Mock Version: 3.5 ENTER ['do_with_status'](['bash', '--login', '-c', '/usr/bin/rpmbuild -bs --target aarch64 --nodeps /builddir/build/SPECS/python-sglang.spec'], chrootPath='/var/lib/mock/openeuler-25.09-aarch64-1787989424.669577/root'env={'TERM': 'vt100', 'SHELL': '/bin/bash', 'HOME': '/builddir', 'HOSTNAME': 'mock', 'PATH': '/usr/bin:/bin:/usr/sbin:/sbin', 'PROMPT_COMMAND': 'printf "\\033]0;\\007"', 'PS1': ' \\s-\\v\\$ ', 'LANG': 'C.UTF-8'}shell=Falselogger=timeout=0uid=1000gid=135user='mockbuild'nspawn_args=[]unshare_net=TrueprintOutput=True) Executing command: ['bash', '--login', '-c', '/usr/bin/rpmbuild -bs --target aarch64 --nodeps /builddir/build/SPECS/python-sglang.spec'] with env {'TERM': 'vt100', 'SHELL': '/bin/bash', 'HOME': '/builddir', 'HOSTNAME': 'mock', 'PATH': '/usr/bin:/bin:/usr/sbin:/sbin', 'PROMPT_COMMAND': 'printf "\\033]0;\\007"', 'PS1': ' \\s-\\v\\$ ', 'LANG': 'C.UTF-8'} and shell False :1: DeprecationWarning: The distutils package is deprecated and slated for removal in Python 3.12. Use setuptools or check PEP 632 for potential alternatives :1: DeprecationWarning: The distutils.sysconfig module is deprecated, use sysconfig instead Building target platforms: aarch64 Building for target aarch64 Wrote: /builddir/build/SRPMS/python-sglang-0.4.6.post5-2.src.rpm Child return code was: 0 Mock Version: 3.5 ENTER ['do_with_status'](['bash', '--login', '-c', '/usr/bin/rpmbuild -bs --target aarch64 --nodeps /builddir/build/SPECS/python-sglang.spec'], chrootPath='/var/lib/mock/openeuler-25.09-aarch64-1787989424.669577/root'env={'TERM': 'vt100', 'SHELL': '/bin/bash', 'HOME': '/builddir', 'HOSTNAME': 'mock', 'PATH': '/usr/bin:/bin:/usr/sbin:/sbin', 'PROMPT_COMMAND': 'printf "\\033]0;\\007"', 'PS1': ' \\s-\\v\\$ ', 'LANG': 'C.UTF-8'}shell=Falselogger=timeout=0uid=1000gid=135user='mockbuild'nspawn_args=[]unshare_net=TrueprintOutput=True) Executing command: ['bash', '--login', '-c', '/usr/bin/rpmbuild -bs --target aarch64 --nodeps /builddir/build/SPECS/python-sglang.spec'] with env {'TERM': 'vt100', 'SHELL': '/bin/bash', 'HOME': '/builddir', 'HOSTNAME': 'mock', 'PATH': '/usr/bin:/bin:/usr/sbin:/sbin', 'PROMPT_COMMAND': 'printf "\\033]0;\\007"', 'PS1': ' \\s-\\v\\$ ', 'LANG': 'C.UTF-8'} and shell False :1: DeprecationWarning: The distutils package is deprecated and slated for removal in Python 3.12. Use setuptools or check PEP 632 for potential alternatives :1: DeprecationWarning: The distutils.sysconfig module is deprecated, use sysconfig instead Building target platforms: aarch64 Building for target aarch64 Wrote: /builddir/build/SRPMS/python-sglang-0.4.6.post5-2.src.rpm Child return code was: 0 ENTER ['do_with_status'](['bash', '--login', '-c', '/usr/bin/rpmbuild -bb --target aarch64 --nodeps /builddir/build/SPECS/python-sglang.spec'], chrootPath='/var/lib/mock/openeuler-25.09-aarch64-1787989424.669577/root'env={'TERM': 'vt100', 'SHELL': '/bin/bash', 'HOME': '/builddir', 'HOSTNAME': 'mock', 'PATH': '/usr/bin:/bin:/usr/sbin:/sbin', 'PROMPT_COMMAND': 'printf "\\033]0;\\007"', 'PS1': ' \\s-\\v\\$ ', 'LANG': 'C.UTF-8'}shell=Falselogger=timeout=0uid=1000gid=135user='mockbuild'nspawn_args=[]unshare_net=TrueprintOutput=True) Executing command: ['bash', '--login', '-c', '/usr/bin/rpmbuild -bb --target aarch64 --nodeps /builddir/build/SPECS/python-sglang.spec'] with env {'TERM': 'vt100', 'SHELL': '/bin/bash', 'HOME': '/builddir', 'HOSTNAME': 'mock', 'PATH': '/usr/bin:/bin:/usr/sbin:/sbin', 'PROMPT_COMMAND': 'printf "\\033]0;\\007"', 'PS1': ' \\s-\\v\\$ ', 'LANG': 'C.UTF-8'} and shell False Building target platforms: aarch64 Building for target aarch64 Executing(%prep): /bin/sh -e /var/tmp/rpm-tmp.rg1atG + umask 022 + cd /builddir/build/BUILD + cd /builddir/build/BUILD + rm -rf sglang-0.4.6.post5 + /usr/lib/rpm/rpmuncompress -x /builddir/build/SOURCES/sglang-0.4.6.post5.tar.gz + STATUS=0 + '[' 0 -ne 0 ']' + cd sglang-0.4.6.post5 + /usr/bin/chmod -Rf a+rX,u+w,g-w,o-w . + RPM_EC=0 ++ jobs -p + exit 0 Executing(%build): /bin/sh -e /var/tmp/rpm-tmp.xxdYMQ + umask 022 + cd /builddir/build/BUILD + cd sglang-0.4.6.post5 + CFLAGS='-O2 -flto=auto -ffat-lto-objects -g -grecord-gcc-switches -pipe -fstack-protector-strong -Wall -Werror=format-security -Wp,-U_FORTIFY_SOURCE,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -specs=/usr/lib/rpm/generic-hardened-cc1 -mbranch-protection=standard -fasynchronous-unwind-tables -fstack-clash-protection' + LDFLAGS='-Wl,-z,relro -Wl,--as-needed -Wl,-z,now -specs=/usr/lib/rpm/generic-hardened-ld -specs=/usr/lib/rpm/openEuler/openEuler-package-notes' + /usr/bin/python3 -mpip wheel --verbose --progress-bar off --disable-pip-version-check --use-pep517 --no-build-isolation --no-deps --wheel-dir ./build . Processing /builddir/build/BUILD/sglang-0.4.6.post5 Preparing metadata (pyproject.toml): started Running command Preparing metadata (pyproject.toml) /usr/lib/python3.11/site-packages/setuptools/config/_apply_pyprojecttoml.py:82: SetuptoolsDeprecationWarning: `project.license` as a TOML table is deprecated !! ******************************************************************************** Please use a simple string containing a SPDX expression for `project.license`. You can also use `project.license-files`. (Both options available on setuptools>=77.0.0). This deprecation is overdue, please update your project and remove deprecated calls to avoid build errors in the future. See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! corresp(dist, value, root_dir) /usr/lib/python3.11/site-packages/setuptools/config/_apply_pyprojecttoml.py:61: SetuptoolsDeprecationWarning: License classifiers are deprecated. !! ******************************************************************************** Please consider removing the following classifiers in favor of a SPDX license expression: License :: OSI Approved :: Apache Software License See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! dist._finalize_license_expression() /usr/lib/python3.11/site-packages/setuptools/dist.py:759: SetuptoolsDeprecationWarning: License classifiers are deprecated. !! ******************************************************************************** Please consider removing the following classifiers in favor of a SPDX license expression: License :: OSI Approved :: Apache Software License See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! self._finalize_license_expression() running dist_info creating /tmp/pip-modern-metadata-12p60hrv/sglang.egg-info writing /tmp/pip-modern-metadata-12p60hrv/sglang.egg-info/PKG-INFO writing dependency_links to /tmp/pip-modern-metadata-12p60hrv/sglang.egg-info/dependency_links.txt writing requirements to /tmp/pip-modern-metadata-12p60hrv/sglang.egg-info/requires.txt writing top-level names to /tmp/pip-modern-metadata-12p60hrv/sglang.egg-info/top_level.txt writing manifest file '/tmp/pip-modern-metadata-12p60hrv/sglang.egg-info/SOURCES.txt' reading manifest file '/tmp/pip-modern-metadata-12p60hrv/sglang.egg-info/SOURCES.txt' adding license file 'LICENSE' writing manifest file '/tmp/pip-modern-metadata-12p60hrv/sglang.egg-info/SOURCES.txt' creating '/tmp/pip-modern-metadata-12p60hrv/sglang-0.4.6.post5.dist-info' Preparing metadata (pyproject.toml): finished with status 'done' Building wheels for collected packages: sglang Building wheel for sglang (pyproject.toml): started Running command Building wheel for sglang (pyproject.toml) /usr/lib/python3.11/site-packages/setuptools/config/_apply_pyprojecttoml.py:82: SetuptoolsDeprecationWarning: `project.license` as a TOML table is deprecated !! ******************************************************************************** Please use a simple string containing a SPDX expression for `project.license`. You can also use `project.license-files`. (Both options available on setuptools>=77.0.0). This deprecation is overdue, please update your project and remove deprecated calls to avoid build errors in the future. See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! corresp(dist, value, root_dir) /usr/lib/python3.11/site-packages/setuptools/config/_apply_pyprojecttoml.py:61: SetuptoolsDeprecationWarning: License classifiers are deprecated. !! ******************************************************************************** Please consider removing the following classifiers in favor of a SPDX license expression: License :: OSI Approved :: Apache Software License See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! dist._finalize_license_expression() /usr/lib/python3.11/site-packages/setuptools/dist.py:759: SetuptoolsDeprecationWarning: License classifiers are deprecated. !! ******************************************************************************** Please consider removing the following classifiers in favor of a SPDX license expression: License :: OSI Approved :: Apache Software License See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! self._finalize_license_expression() running bdist_wheel running build running build_py creating build/lib/sglang copying sglang/bench_one_batch.py -> build/lib/sglang copying sglang/launch_server.py -> build/lib/sglang copying sglang/version.py -> build/lib/sglang copying sglang/bench_serving.py -> build/lib/sglang copying sglang/check_env.py -> build/lib/sglang copying sglang/compile_deep_gemm.py -> build/lib/sglang copying sglang/bench_one_batch_server.py -> build/lib/sglang copying sglang/utils.py -> build/lib/sglang copying sglang/bench_offline_throughput.py -> build/lib/sglang copying sglang/api.py -> build/lib/sglang copying sglang/__init__.py -> build/lib/sglang copying sglang/global_config.py -> build/lib/sglang creating build/lib/sglang/srt copying sglang/srt/operations_strategy.py -> build/lib/sglang/srt copying sglang/srt/mm_utils.py -> build/lib/sglang/srt copying sglang/srt/model_parallel.py -> build/lib/sglang/srt copying sglang/srt/reasoning_parser.py -> build/lib/sglang/srt copying sglang/srt/patch_torch.py -> build/lib/sglang/srt copying sglang/srt/code_completion_parser.py -> build/lib/sglang/srt copying sglang/srt/operations.py -> build/lib/sglang/srt copying sglang/srt/_custom_ops.py -> build/lib/sglang/srt copying sglang/srt/server_args.py -> build/lib/sglang/srt copying sglang/srt/conversation.py -> build/lib/sglang/srt copying sglang/srt/custom_op.py -> build/lib/sglang/srt copying sglang/srt/utils.py -> build/lib/sglang/srt copying sglang/srt/hf_transformers_utils.py -> build/lib/sglang/srt copying sglang/srt/torch_memory_saver_adapter.py -> build/lib/sglang/srt copying sglang/srt/warmup.py -> build/lib/sglang/srt copying sglang/srt/aio_rwlock.py -> build/lib/sglang/srt creating build/lib/sglang/test copying sglang/test/few_shot_gsm8k_engine.py -> build/lib/sglang/test copying sglang/test/simple_eval_gpqa.py -> build/lib/sglang/test copying sglang/test/simple_eval_math.py -> build/lib/sglang/test copying sglang/test/test_dynamic_grad_mode.py -> build/lib/sglang/test copying sglang/test/simple_eval_common.py -> build/lib/sglang/test copying sglang/test/test_block_fp8_ep.py -> build/lib/sglang/test copying sglang/test/simple_eval_humaneval.py -> build/lib/sglang/test copying sglang/test/test_layernorm.py -> build/lib/sglang/test copying sglang/test/few_shot_gsm8k.py -> build/lib/sglang/test copying sglang/test/test_activation.py -> build/lib/sglang/test copying sglang/test/test_block_fp8.py -> build/lib/sglang/test copying sglang/test/runners.py -> build/lib/sglang/test copying sglang/test/test_utils.py -> build/lib/sglang/test copying sglang/test/test_custom_ops.py -> build/lib/sglang/test copying sglang/test/test_deepep_utils.py -> build/lib/sglang/test copying sglang/test/run_eval.py -> build/lib/sglang/test copying sglang/test/send_one.py -> build/lib/sglang/test copying sglang/test/__init__.py -> build/lib/sglang/test copying sglang/test/test_cutlass_moe.py -> build/lib/sglang/test copying sglang/test/simple_eval_mgsm.py -> build/lib/sglang/test copying sglang/test/simple_eval_mmlu.py -> build/lib/sglang/test copying sglang/test/test_programs.py -> build/lib/sglang/test creating build/lib/sglang/eval copying sglang/eval/llama3_eval.py -> build/lib/sglang/eval copying sglang/eval/loogle_eval.py -> build/lib/sglang/eval creating build/lib/sglang/lang copying sglang/lang/chat_template.py -> build/lib/sglang/lang copying sglang/lang/choices.py -> build/lib/sglang/lang copying sglang/lang/interpreter.py -> build/lib/sglang/lang copying sglang/lang/tracer.py -> build/lib/sglang/lang copying sglang/lang/compiler.py -> build/lib/sglang/lang copying sglang/lang/ir.py -> build/lib/sglang/lang creating build/lib/sglang/srt/metrics copying sglang/srt/metrics/func_timer.py -> build/lib/sglang/srt/metrics copying sglang/srt/metrics/collector.py -> build/lib/sglang/srt/metrics creating build/lib/sglang/srt/layers copying sglang/srt/layers/sampler.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/linear.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/dp_attention.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/logits_processor.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/torchao_utils.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/layernorm.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/radix_attention.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/multimodal.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/rotary_embedding.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/parameter.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/pooler.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/elementwise.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/activation.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/utils.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/communicator.py -> build/lib/sglang/srt/layers copying sglang/srt/layers/vocab_parallel_embedding.py -> build/lib/sglang/srt/layers creating build/lib/sglang/srt/constrained copying sglang/srt/constrained/xgrammar_backend.py -> build/lib/sglang/srt/constrained copying sglang/srt/constrained/reasoner_grammar_backend.py -> build/lib/sglang/srt/constrained copying sglang/srt/constrained/outlines_jump_forward.py -> build/lib/sglang/srt/constrained copying sglang/srt/constrained/base_grammar_backend.py -> build/lib/sglang/srt/constrained copying sglang/srt/constrained/llguidance_backend.py -> build/lib/sglang/srt/constrained copying sglang/srt/constrained/outlines_backend.py -> build/lib/sglang/srt/constrained creating build/lib/sglang/srt/model_loader copying sglang/srt/model_loader/utils.py -> build/lib/sglang/srt/model_loader copying sglang/srt/model_loader/weight_utils.py -> build/lib/sglang/srt/model_loader copying sglang/srt/model_loader/__init__.py -> build/lib/sglang/srt/model_loader copying sglang/srt/model_loader/loader.py -> build/lib/sglang/srt/model_loader creating build/lib/sglang/srt/lora copying sglang/srt/lora/lora_config.py -> build/lib/sglang/srt/lora copying sglang/srt/lora/lora_manager.py -> build/lib/sglang/srt/lora copying sglang/srt/lora/layers.py -> build/lib/sglang/srt/lora copying sglang/srt/lora/utils.py -> build/lib/sglang/srt/lora copying sglang/srt/lora/lora.py -> build/lib/sglang/srt/lora copying sglang/srt/lora/mem_pool.py -> build/lib/sglang/srt/lora creating build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/paged_allocator.py -> build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/flush_cache.py -> build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/radix_cache.py -> build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/hiradix_cache.py -> build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/chunk_cache.py -> build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/multimodal_cache.py -> build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/memory_pool.py -> build/lib/sglang/srt/mem_cache copying sglang/srt/mem_cache/base_prefix_cache.py -> build/lib/sglang/srt/mem_cache creating build/lib/sglang/srt/configs copying sglang/srt/configs/kimi_vl.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/model_config.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/device_config.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/exaone.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/deepseekvl2.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/kimi_vl_moonvit.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/internvl.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/janus_pro.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/utils.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/chatglm.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/load_config.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/dbrx.py -> build/lib/sglang/srt/configs copying sglang/srt/configs/__init__.py -> build/lib/sglang/srt/configs creating build/lib/sglang/srt/sampling copying sglang/srt/sampling/sampling_params.py -> build/lib/sglang/srt/sampling copying sglang/srt/sampling/custom_logit_processor.py -> build/lib/sglang/srt/sampling copying sglang/srt/sampling/sampling_batch_info.py -> build/lib/sglang/srt/sampling creating build/lib/sglang/srt/managers copying sglang/srt/managers/schedule_policy.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/eplb_manager.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/detokenizer_manager.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/scheduler.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/deepseek_eplb.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/cache_controller.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/expert_location_dispatch.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/mm_utils.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/session_controller.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/io_struct.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/tp_worker.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/scheduler_output_processor_mixin.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/expert_distribution.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/data_parallel_controller.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/schedule_batch.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/utils.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/tp_worker_overlap_thread.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/multimodal_processor.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/configure_logging.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/tokenizer_manager.py -> build/lib/sglang/srt/managers copying sglang/srt/managers/expert_location.py -> build/lib/sglang/srt/managers creating build/lib/sglang/srt/model_executor copying sglang/srt/model_executor/expert_location_updater.py -> build/lib/sglang/srt/model_executor copying sglang/srt/model_executor/model_runner.py -> build/lib/sglang/srt/model_executor copying sglang/srt/model_executor/cuda_graph_runner.py -> build/lib/sglang/srt/model_executor copying sglang/srt/model_executor/forward_batch_info.py -> build/lib/sglang/srt/model_executor creating build/lib/sglang/srt/function_call copying sglang/srt/function_call/core_types.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/base_format_detector.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/ebnf_composer.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/pythonic_detector.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/qwen25_detector.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/deepseekv3_detector.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/mistral_detector.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/llama32_detector.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/function_call_parser.py -> build/lib/sglang/srt/function_call copying sglang/srt/function_call/utils.py -> build/lib/sglang/srt/function_call creating build/lib/sglang/srt/connector copying sglang/srt/connector/s3.py -> build/lib/sglang/srt/connector copying sglang/srt/connector/base_connector.py -> build/lib/sglang/srt/connector copying sglang/srt/connector/redis.py -> build/lib/sglang/srt/connector copying sglang/srt/connector/utils.py -> build/lib/sglang/srt/connector copying sglang/srt/connector/__init__.py -> build/lib/sglang/srt/connector creating build/lib/sglang/srt/distributed copying sglang/srt/distributed/communication_op.py -> build/lib/sglang/srt/distributed copying sglang/srt/distributed/parallel_state.py -> build/lib/sglang/srt/distributed copying sglang/srt/distributed/utils.py -> build/lib/sglang/srt/distributed copying sglang/srt/distributed/__init__.py -> build/lib/sglang/srt/distributed creating build/lib/sglang/srt/disaggregation copying sglang/srt/disaggregation/decode_schedule_batch_mixin.py -> build/lib/sglang/srt/disaggregation copying sglang/srt/disaggregation/mini_lb.py -> build/lib/sglang/srt/disaggregation copying sglang/srt/disaggregation/prefill.py -> build/lib/sglang/srt/disaggregation copying sglang/srt/disaggregation/utils.py -> build/lib/sglang/srt/disaggregation copying sglang/srt/disaggregation/kv_events.py -> build/lib/sglang/srt/disaggregation copying sglang/srt/disaggregation/decode.py -> build/lib/sglang/srt/disaggregation creating build/lib/sglang/srt/entrypoints copying sglang/srt/entrypoints/EngineBase.py -> build/lib/sglang/srt/entrypoints copying sglang/srt/entrypoints/engine.py -> build/lib/sglang/srt/entrypoints copying sglang/srt/entrypoints/http_server.py -> build/lib/sglang/srt/entrypoints copying sglang/srt/entrypoints/http_server_engine.py -> build/lib/sglang/srt/entrypoints copying sglang/srt/entrypoints/verl_engine.py -> build/lib/sglang/srt/entrypoints creating build/lib/sglang/srt/speculative copying sglang/srt/speculative/eagle_worker.py -> build/lib/sglang/srt/speculative copying sglang/srt/speculative/eagle_utils.py -> build/lib/sglang/srt/speculative copying sglang/srt/speculative/eagle_draft_cuda_graph_runner.py -> build/lib/sglang/srt/speculative copying sglang/srt/speculative/build_eagle_tree.py -> build/lib/sglang/srt/speculative copying sglang/srt/speculative/spec_info.py -> build/lib/sglang/srt/speculative creating build/lib/sglang/srt/models copying sglang/srt/models/gemma2.py -> build/lib/sglang/srt/models copying sglang/srt/models/mllama.py -> build/lib/sglang/srt/models copying sglang/srt/models/llama4.py -> build/lib/sglang/srt/models copying sglang/srt/models/xverse.py -> build/lib/sglang/srt/models copying sglang/srt/models/grok.py -> build/lib/sglang/srt/models copying sglang/srt/models/llama_classification.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen2_moe.py -> build/lib/sglang/srt/models copying sglang/srt/models/yivl.py -> build/lib/sglang/srt/models copying sglang/srt/models/llava.py -> build/lib/sglang/srt/models copying sglang/srt/models/minicpmv.py -> build/lib/sglang/srt/models copying sglang/srt/models/gemma2_reward.py -> build/lib/sglang/srt/models copying sglang/srt/models/commandr.py -> build/lib/sglang/srt/models copying sglang/srt/models/siglip.py -> build/lib/sglang/srt/models copying sglang/srt/models/minicpm3.py -> build/lib/sglang/srt/models copying sglang/srt/models/llama_eagle.py -> build/lib/sglang/srt/models copying sglang/srt/models/llavavid.py -> build/lib/sglang/srt/models copying sglang/srt/models/kimi_vl.py -> build/lib/sglang/srt/models copying sglang/srt/models/minicpmo.py -> build/lib/sglang/srt/models copying sglang/srt/models/gpt2.py -> build/lib/sglang/srt/models copying sglang/srt/models/phi3_small.py -> build/lib/sglang/srt/models copying sglang/srt/models/deepseek.py -> build/lib/sglang/srt/models copying sglang/srt/models/exaone.py -> build/lib/sglang/srt/models copying sglang/srt/models/gemma.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen3.py -> build/lib/sglang/srt/models copying sglang/srt/models/olmo.py -> build/lib/sglang/srt/models copying sglang/srt/models/internlm2.py -> build/lib/sglang/srt/models copying sglang/srt/models/xverse_moe.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen2_rm.py -> build/lib/sglang/srt/models copying sglang/srt/models/kimi_vl_moonvit.py -> build/lib/sglang/srt/models copying sglang/srt/models/roberta.py -> build/lib/sglang/srt/models copying sglang/srt/models/olmo2.py -> build/lib/sglang/srt/models copying sglang/srt/models/clip.py -> build/lib/sglang/srt/models copying sglang/srt/models/deepseek_nextn.py -> build/lib/sglang/srt/models copying sglang/srt/models/mixtral_quant.py -> build/lib/sglang/srt/models copying sglang/srt/models/bert.py -> build/lib/sglang/srt/models copying sglang/srt/models/mllama4.py -> build/lib/sglang/srt/models copying sglang/srt/models/olmoe.py -> build/lib/sglang/srt/models copying sglang/srt/models/internvl.py -> build/lib/sglang/srt/models copying sglang/srt/models/torch_native_llama.py -> build/lib/sglang/srt/models copying sglang/srt/models/registry.py -> build/lib/sglang/srt/models copying sglang/srt/models/internlm2_reward.py -> build/lib/sglang/srt/models copying sglang/srt/models/mixtral.py -> build/lib/sglang/srt/models copying sglang/srt/models/gemma3_mm.py -> build/lib/sglang/srt/models copying sglang/srt/models/mistral.py -> build/lib/sglang/srt/models copying sglang/srt/models/gemma3_causal.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen2_5_vl.py -> build/lib/sglang/srt/models copying sglang/srt/models/llama_embedding.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen2_vl.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen.py -> build/lib/sglang/srt/models copying sglang/srt/models/minicpm.py -> build/lib/sglang/srt/models copying sglang/srt/models/deepseek_v2.py -> build/lib/sglang/srt/models copying sglang/srt/models/mimo.py -> build/lib/sglang/srt/models copying sglang/srt/models/deepseek_janus_pro.py -> build/lib/sglang/srt/models copying sglang/srt/models/chatglm.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen2.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen3_moe.py -> build/lib/sglang/srt/models copying sglang/srt/models/baichuan.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen2_classification.py -> build/lib/sglang/srt/models copying sglang/srt/models/dbrx.py -> build/lib/sglang/srt/models copying sglang/srt/models/llama.py -> build/lib/sglang/srt/models copying sglang/srt/models/llama_eagle3.py -> build/lib/sglang/srt/models copying sglang/srt/models/llama_reward.py -> build/lib/sglang/srt/models copying sglang/srt/models/gpt_bigcode.py -> build/lib/sglang/srt/models copying sglang/srt/models/deepseek_vl2.py -> build/lib/sglang/srt/models copying sglang/srt/models/pixtral.py -> build/lib/sglang/srt/models copying sglang/srt/models/stablelm.py -> build/lib/sglang/srt/models copying sglang/srt/models/mimo_mtp.py -> build/lib/sglang/srt/models copying sglang/srt/models/qwen2_eagle.py -> build/lib/sglang/srt/models copying sglang/srt/models/granite.py -> build/lib/sglang/srt/models creating build/lib/sglang/srt/openai_api copying sglang/srt/openai_api/protocol.py -> build/lib/sglang/srt/openai_api copying sglang/srt/openai_api/adapter.py -> build/lib/sglang/srt/openai_api creating build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/int8_kernel.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/base_config.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/fp8_kernel.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/fp8.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/w8a8_fp8.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/w8a8_int8.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/qoq.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/blockwise_int8.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/deep_gemm.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/kv_cache.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/awq.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/utils.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/gptq.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/__init__.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/moe_wna16.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/modelopt_quant.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/fp8_utils.py -> build/lib/sglang/srt/layers/quantization copying sglang/srt/layers/quantization/int8_utils.py -> build/lib/sglang/srt/layers/quantization creating build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/flashmla_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/flashinfer_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/aiter_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/torch_native_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/triton_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/vision.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/utils.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/flashinfer_mla_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/cutlass_mla_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/flashattention_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/base_attn_backend.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/merge_state.py -> build/lib/sglang/srt/layers/attention copying sglang/srt/layers/attention/double_sparsity_backend.py -> build/lib/sglang/srt/layers/attention creating build/lib/sglang/srt/layers/moe copying sglang/srt/layers/moe/cutlass_moe.py -> build/lib/sglang/srt/layers/moe copying sglang/srt/layers/moe/topk.py -> build/lib/sglang/srt/layers/moe copying sglang/srt/layers/moe/router.py -> build/lib/sglang/srt/layers/moe copying sglang/srt/layers/moe/fused_moe_native.py -> build/lib/sglang/srt/layers/moe creating build/lib/sglang/srt/layers/quantization/compressed_tensors copying sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors copying sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors copying sglang/srt/layers/quantization/compressed_tensors/utils.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors copying sglang/srt/layers/quantization/compressed_tensors/__init__.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors creating build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes copying sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes copying sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes copying sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes copying sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py -> build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes creating build/lib/sglang/srt/layers/attention/triton_ops copying sglang/srt/layers/attention/triton_ops/extend_attention.py -> build/lib/sglang/srt/layers/attention/triton_ops copying sglang/srt/layers/attention/triton_ops/prefill_attention.py -> build/lib/sglang/srt/layers/attention/triton_ops copying sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py -> build/lib/sglang/srt/layers/attention/triton_ops copying sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py -> build/lib/sglang/srt/layers/attention/triton_ops copying sglang/srt/layers/attention/triton_ops/decode_attention.py -> build/lib/sglang/srt/layers/attention/triton_ops copying sglang/srt/layers/attention/triton_ops/merge_state.py -> build/lib/sglang/srt/layers/attention/triton_ops creating build/lib/sglang/srt/layers/moe/ep_moe copying sglang/srt/layers/moe/ep_moe/kernels.py -> build/lib/sglang/srt/layers/moe/ep_moe copying sglang/srt/layers/moe/ep_moe/layer.py -> build/lib/sglang/srt/layers/moe/ep_moe copying sglang/srt/layers/moe/ep_moe/token_dispatcher.py -> build/lib/sglang/srt/layers/moe/ep_moe copying sglang/srt/layers/moe/ep_moe/__init__.py -> build/lib/sglang/srt/layers/moe/ep_moe creating build/lib/sglang/srt/layers/moe/fused_moe_triton copying sglang/srt/layers/moe/fused_moe_triton/layer.py -> build/lib/sglang/srt/layers/moe/fused_moe_triton copying sglang/srt/layers/moe/fused_moe_triton/fused_moe.py -> build/lib/sglang/srt/layers/moe/fused_moe_triton copying sglang/srt/layers/moe/fused_moe_triton/__init__.py -> build/lib/sglang/srt/layers/moe/fused_moe_triton creating build/lib/sglang/srt/constrained/triton_ops copying sglang/srt/constrained/triton_ops/bitmask_ops.py -> build/lib/sglang/srt/constrained/triton_ops creating build/lib/sglang/srt/lora/backend copying sglang/srt/lora/backend/base_backend.py -> build/lib/sglang/srt/lora/backend copying sglang/srt/lora/backend/flashinfer_backend.py -> build/lib/sglang/srt/lora/backend copying sglang/srt/lora/backend/triton_backend.py -> build/lib/sglang/srt/lora/backend creating build/lib/sglang/srt/lora/triton_ops copying sglang/srt/lora/triton_ops/qkv_lora_b.py -> build/lib/sglang/srt/lora/triton_ops copying sglang/srt/lora/triton_ops/sgemm_lora_a.py -> build/lib/sglang/srt/lora/triton_ops copying sglang/srt/lora/triton_ops/gate_up_lora_b.py -> build/lib/sglang/srt/lora/triton_ops copying sglang/srt/lora/triton_ops/sgemm_lora_b.py -> build/lib/sglang/srt/lora/triton_ops copying sglang/srt/lora/triton_ops/__init__.py -> build/lib/sglang/srt/lora/triton_ops creating build/lib/sglang/srt/sampling/penaltylib copying sglang/srt/sampling/penaltylib/frequency_penalty.py -> build/lib/sglang/srt/sampling/penaltylib copying sglang/srt/sampling/penaltylib/min_new_tokens.py -> build/lib/sglang/srt/sampling/penaltylib copying sglang/srt/sampling/penaltylib/presence_penalty.py -> build/lib/sglang/srt/sampling/penaltylib copying sglang/srt/sampling/penaltylib/__init__.py -> build/lib/sglang/srt/sampling/penaltylib copying sglang/srt/sampling/penaltylib/orchestrator.py -> build/lib/sglang/srt/sampling/penaltylib creating build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/llava.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/mlama.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/kimi_vl.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/gemma3.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/base_processor.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/clip.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/mllama4.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/internvl.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/janus_pro.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/minicpm.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/qwen_vl.py -> build/lib/sglang/srt/managers/multimodal_processors copying sglang/srt/managers/multimodal_processors/pixtral.py -> build/lib/sglang/srt/managers/multimodal_processors creating build/lib/sglang/srt/connector/serde copying sglang/srt/connector/serde/serde.py -> build/lib/sglang/srt/connector/serde copying sglang/srt/connector/serde/__init__.py -> build/lib/sglang/srt/connector/serde copying sglang/srt/connector/serde/safe_serde.py -> build/lib/sglang/srt/connector/serde creating build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/hpu_communicator.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/custom_all_reduce.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/xpu_communicator.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/pynccl_wrapper.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/cuda_wrapper.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/shm_broadcast.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/pynccl.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py -> build/lib/sglang/srt/distributed/device_communicators copying sglang/srt/distributed/device_communicators/npu_communicator.py -> build/lib/sglang/srt/distributed/device_communicators creating build/lib/sglang/srt/disaggregation/fake copying sglang/srt/disaggregation/fake/conn.py -> build/lib/sglang/srt/disaggregation/fake copying sglang/srt/disaggregation/fake/__init__.py -> build/lib/sglang/srt/disaggregation/fake creating build/lib/sglang/srt/disaggregation/mooncake copying sglang/srt/disaggregation/mooncake/conn.py -> build/lib/sglang/srt/disaggregation/mooncake copying sglang/srt/disaggregation/mooncake/transfer_engine.py -> build/lib/sglang/srt/disaggregation/mooncake copying sglang/srt/disaggregation/mooncake/__init__.py -> build/lib/sglang/srt/disaggregation/mooncake creating build/lib/sglang/srt/disaggregation/base copying sglang/srt/disaggregation/base/conn.py -> build/lib/sglang/srt/disaggregation/base copying sglang/srt/disaggregation/base/__init__.py -> build/lib/sglang/srt/disaggregation/base creating build/lib/sglang/srt/disaggregation/nixl copying sglang/srt/disaggregation/nixl/conn.py -> build/lib/sglang/srt/disaggregation/nixl copying sglang/srt/disaggregation/nixl/__init__.py -> build/lib/sglang/srt/disaggregation/nixl creating build/lib/sglang/test/attention copying sglang/test/attention/test_flashattn_mla_backend.py -> build/lib/sglang/test/attention copying sglang/test/attention/test_prefix_chunk_info.py -> build/lib/sglang/test/attention copying sglang/test/attention/test_flashattn_backend.py -> build/lib/sglang/test/attention copying sglang/test/attention/__init__.py -> build/lib/sglang/test/attention creating build/lib/sglang/lang/backend copying sglang/lang/backend/anthropic.py -> build/lib/sglang/lang/backend copying sglang/lang/backend/base_backend.py -> build/lib/sglang/lang/backend copying sglang/lang/backend/vertexai.py -> build/lib/sglang/lang/backend copying sglang/lang/backend/litellm.py -> build/lib/sglang/lang/backend copying sglang/lang/backend/runtime_endpoint.py -> build/lib/sglang/lang/backend copying sglang/lang/backend/openai.py -> build/lib/sglang/lang/backend copying sglang/lang/backend/__init__.py -> build/lib/sglang/lang/backend running egg_info writing sglang.egg-info/PKG-INFO writing dependency_links to sglang.egg-info/dependency_links.txt writing requirements to sglang.egg-info/requires.txt writing top-level names to sglang.egg-info/top_level.txt reading manifest file 'sglang.egg-info/SOURCES.txt' adding license file 'LICENSE' writing manifest file 'sglang.egg-info/SOURCES.txt' creating build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Radeon_Graphics.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Radeon_Graphics.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_L40S.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H20.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Radeon_Graphics.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Radeon_Graphics.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=96,device_name=NVIDIA_H20.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs copying sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json -> build/lib/sglang/srt/layers/moe/fused_moe_triton/configs creating build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs copying sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/lib/sglang/srt/layers/quantization/configs installing to build/bdist.linux-aarch64/wheel running install running install_lib creating build/bdist.linux-aarch64/wheel creating build/bdist.linux-aarch64/wheel/sglang copying build/lib/sglang/bench_one_batch.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/launch_server.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/version.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/bench_serving.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/check_env.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/compile_deep_gemm.py -> build/bdist.linux-aarch64/wheel/./sglang creating build/bdist.linux-aarch64/wheel/sglang/srt creating build/bdist.linux-aarch64/wheel/sglang/srt/metrics copying build/lib/sglang/srt/metrics/func_timer.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/metrics copying build/lib/sglang/srt/metrics/collector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/metrics copying build/lib/sglang/srt/operations_strategy.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/mm_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/model_parallel.py -> build/bdist.linux-aarch64/wheel/./sglang/srt creating build/bdist.linux-aarch64/wheel/sglang/srt/layers copying build/lib/sglang/srt/layers/sampler.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/linear.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/dp_attention.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/logits_processor.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/torchao_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/layernorm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/radix_attention.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/multimodal.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/rotary_embedding.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/parameter.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/pooler.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/elementwise.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/activation.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/int8_kernel.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/base_config.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/fp8_kernel.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/fp8.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/quantization/compressed_tensors copying build/lib/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors copying build/lib/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/quantization/compressed_tensors/schemes copying build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors/schemes copying build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors/schemes copying build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors/schemes copying build/lib/sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors/schemes copying build/lib/sglang/srt/layers/quantization/compressed_tensors/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors copying build/lib/sglang/srt/layers/quantization/compressed_tensors/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/compressed_tensors copying build/lib/sglang/srt/layers/quantization/w8a8_fp8.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/w8a8_int8.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/qoq.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization/configs copying build/lib/sglang/srt/layers/quantization/blockwise_int8.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/deep_gemm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/kv_cache.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/awq.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/gptq.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/moe_wna16.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/modelopt_quant.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/fp8_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization copying build/lib/sglang/srt/layers/quantization/int8_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/quantization creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/flashmla_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/flashinfer_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/aiter_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/attention/triton_ops copying build/lib/sglang/srt/layers/attention/triton_ops/extend_attention.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention/triton_ops copying build/lib/sglang/srt/layers/attention/triton_ops/prefill_attention.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention/triton_ops copying build/lib/sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention/triton_ops copying build/lib/sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention/triton_ops copying build/lib/sglang/srt/layers/attention/triton_ops/decode_attention.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention/triton_ops copying build/lib/sglang/srt/layers/attention/triton_ops/merge_state.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention/triton_ops copying build/lib/sglang/srt/layers/attention/torch_native_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/triton_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/vision.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/flashinfer_mla_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/cutlass_mla_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/flashattention_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/base_attn_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/merge_state.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/attention/double_sparsity_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/attention copying build/lib/sglang/srt/layers/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/moe copying build/lib/sglang/srt/layers/moe/cutlass_moe.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/moe/ep_moe copying build/lib/sglang/srt/layers/moe/ep_moe/kernels.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/ep_moe copying build/lib/sglang/srt/layers/moe/ep_moe/layer.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/ep_moe copying build/lib/sglang/srt/layers/moe/ep_moe/token_dispatcher.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/ep_moe copying build/lib/sglang/srt/layers/moe/ep_moe/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/ep_moe copying build/lib/sglang/srt/layers/moe/topk.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe copying build/lib/sglang/srt/layers/moe/router.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe copying build/lib/sglang/srt/layers/moe/fused_moe_native.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/moe/fused_moe_triton copying build/lib/sglang/srt/layers/moe/fused_moe_triton/layer.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton copying build/lib/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton creating build/bdist.linux-aarch64/wheel/sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Radeon_Graphics.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Radeon_Graphics.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_L40S.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H20.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Radeon_Graphics.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Radeon_Graphics.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=96,device_name=NVIDIA_H20.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton/configs copying build/lib/sglang/srt/layers/moe/fused_moe_triton/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers/moe/fused_moe_triton copying build/lib/sglang/srt/layers/communicator.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers copying build/lib/sglang/srt/layers/vocab_parallel_embedding.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/layers creating build/bdist.linux-aarch64/wheel/sglang/srt/constrained copying build/lib/sglang/srt/constrained/xgrammar_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/constrained copying build/lib/sglang/srt/constrained/reasoner_grammar_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/constrained copying build/lib/sglang/srt/constrained/outlines_jump_forward.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/constrained creating build/bdist.linux-aarch64/wheel/sglang/srt/constrained/triton_ops copying build/lib/sglang/srt/constrained/triton_ops/bitmask_ops.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/constrained/triton_ops copying build/lib/sglang/srt/constrained/base_grammar_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/constrained copying build/lib/sglang/srt/constrained/llguidance_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/constrained copying build/lib/sglang/srt/constrained/outlines_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/constrained copying build/lib/sglang/srt/reasoning_parser.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/patch_torch.py -> build/bdist.linux-aarch64/wheel/./sglang/srt creating build/bdist.linux-aarch64/wheel/sglang/srt/model_loader copying build/lib/sglang/srt/model_loader/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_loader copying build/lib/sglang/srt/model_loader/weight_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_loader copying build/lib/sglang/srt/model_loader/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_loader copying build/lib/sglang/srt/model_loader/loader.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_loader creating build/bdist.linux-aarch64/wheel/sglang/srt/lora copying build/lib/sglang/srt/lora/lora_config.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora creating build/bdist.linux-aarch64/wheel/sglang/srt/lora/backend copying build/lib/sglang/srt/lora/backend/base_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/backend copying build/lib/sglang/srt/lora/backend/flashinfer_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/backend copying build/lib/sglang/srt/lora/backend/triton_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/backend copying build/lib/sglang/srt/lora/lora_manager.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora creating build/bdist.linux-aarch64/wheel/sglang/srt/lora/triton_ops copying build/lib/sglang/srt/lora/triton_ops/qkv_lora_b.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/triton_ops copying build/lib/sglang/srt/lora/triton_ops/sgemm_lora_a.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/triton_ops copying build/lib/sglang/srt/lora/triton_ops/gate_up_lora_b.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/triton_ops copying build/lib/sglang/srt/lora/triton_ops/sgemm_lora_b.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/triton_ops copying build/lib/sglang/srt/lora/triton_ops/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora/triton_ops copying build/lib/sglang/srt/lora/layers.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora copying build/lib/sglang/srt/lora/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora copying build/lib/sglang/srt/lora/lora.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora copying build/lib/sglang/srt/lora/mem_pool.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/lora creating build/bdist.linux-aarch64/wheel/sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/paged_allocator.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/flush_cache.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/radix_cache.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/hiradix_cache.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/chunk_cache.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/multimodal_cache.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/memory_pool.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache copying build/lib/sglang/srt/mem_cache/base_prefix_cache.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/mem_cache creating build/bdist.linux-aarch64/wheel/sglang/srt/configs copying build/lib/sglang/srt/configs/kimi_vl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/model_config.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/device_config.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/exaone.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/deepseekvl2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/kimi_vl_moonvit.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/internvl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/janus_pro.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/chatglm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/load_config.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/dbrx.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/configs/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/configs copying build/lib/sglang/srt/code_completion_parser.py -> build/bdist.linux-aarch64/wheel/./sglang/srt creating build/bdist.linux-aarch64/wheel/sglang/srt/sampling copying build/lib/sglang/srt/sampling/sampling_params.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling copying build/lib/sglang/srt/sampling/custom_logit_processor.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling copying build/lib/sglang/srt/sampling/sampling_batch_info.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling creating build/bdist.linux-aarch64/wheel/sglang/srt/sampling/penaltylib copying build/lib/sglang/srt/sampling/penaltylib/frequency_penalty.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling/penaltylib copying build/lib/sglang/srt/sampling/penaltylib/min_new_tokens.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling/penaltylib copying build/lib/sglang/srt/sampling/penaltylib/presence_penalty.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling/penaltylib copying build/lib/sglang/srt/sampling/penaltylib/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling/penaltylib copying build/lib/sglang/srt/sampling/penaltylib/orchestrator.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/sampling/penaltylib creating build/bdist.linux-aarch64/wheel/sglang/srt/managers copying build/lib/sglang/srt/managers/schedule_policy.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/eplb_manager.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/detokenizer_manager.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/scheduler.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/deepseek_eplb.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/cache_controller.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/expert_location_dispatch.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/mm_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/session_controller.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/io_struct.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/tp_worker.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/scheduler_output_processor_mixin.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/expert_distribution.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/data_parallel_controller.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers creating build/bdist.linux-aarch64/wheel/sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/llava.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/mlama.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/kimi_vl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/gemma3.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/base_processor.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/clip.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/mllama4.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/internvl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/janus_pro.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/minicpm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/qwen_vl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/multimodal_processors/pixtral.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers/multimodal_processors copying build/lib/sglang/srt/managers/schedule_batch.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/tp_worker_overlap_thread.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/multimodal_processor.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/configure_logging.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/tokenizer_manager.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/managers/expert_location.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/managers copying build/lib/sglang/srt/operations.py -> build/bdist.linux-aarch64/wheel/./sglang/srt creating build/bdist.linux-aarch64/wheel/sglang/srt/model_executor copying build/lib/sglang/srt/model_executor/expert_location_updater.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_executor copying build/lib/sglang/srt/model_executor/model_runner.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_executor copying build/lib/sglang/srt/model_executor/cuda_graph_runner.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_executor copying build/lib/sglang/srt/model_executor/forward_batch_info.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/model_executor copying build/lib/sglang/srt/_custom_ops.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/server_args.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/conversation.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/custom_op.py -> build/bdist.linux-aarch64/wheel/./sglang/srt creating build/bdist.linux-aarch64/wheel/sglang/srt/function_call copying build/lib/sglang/srt/function_call/core_types.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/base_format_detector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/ebnf_composer.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/pythonic_detector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/qwen25_detector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/deepseekv3_detector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/mistral_detector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/llama32_detector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/function_call_parser.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call copying build/lib/sglang/srt/function_call/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/function_call creating build/bdist.linux-aarch64/wheel/sglang/srt/connector copying build/lib/sglang/srt/connector/s3.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector creating build/bdist.linux-aarch64/wheel/sglang/srt/connector/serde copying build/lib/sglang/srt/connector/serde/serde.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector/serde copying build/lib/sglang/srt/connector/serde/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector/serde copying build/lib/sglang/srt/connector/serde/safe_serde.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector/serde copying build/lib/sglang/srt/connector/base_connector.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector copying build/lib/sglang/srt/connector/redis.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector copying build/lib/sglang/srt/connector/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector copying build/lib/sglang/srt/connector/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/connector creating build/bdist.linux-aarch64/wheel/sglang/srt/distributed copying build/lib/sglang/srt/distributed/communication_op.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed copying build/lib/sglang/srt/distributed/parallel_state.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed creating build/bdist.linux-aarch64/wheel/sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/hpu_communicator.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/custom_all_reduce.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/xpu_communicator.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/pynccl_wrapper.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/cuda_wrapper.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/shm_broadcast.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/pynccl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/device_communicators/npu_communicator.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed/device_communicators copying build/lib/sglang/srt/distributed/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed copying build/lib/sglang/srt/distributed/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/distributed copying build/lib/sglang/srt/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/hf_transformers_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/torch_memory_saver_adapter.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/warmup.py -> build/bdist.linux-aarch64/wheel/./sglang/srt copying build/lib/sglang/srt/aio_rwlock.py -> build/bdist.linux-aarch64/wheel/./sglang/srt creating build/bdist.linux-aarch64/wheel/sglang/srt/disaggregation creating build/bdist.linux-aarch64/wheel/sglang/srt/disaggregation/fake copying build/lib/sglang/srt/disaggregation/fake/conn.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/fake copying build/lib/sglang/srt/disaggregation/fake/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/fake creating build/bdist.linux-aarch64/wheel/sglang/srt/disaggregation/mooncake copying build/lib/sglang/srt/disaggregation/mooncake/conn.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/mooncake copying build/lib/sglang/srt/disaggregation/mooncake/transfer_engine.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/mooncake copying build/lib/sglang/srt/disaggregation/mooncake/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/mooncake copying build/lib/sglang/srt/disaggregation/decode_schedule_batch_mixin.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation copying build/lib/sglang/srt/disaggregation/mini_lb.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation copying build/lib/sglang/srt/disaggregation/prefill.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation copying build/lib/sglang/srt/disaggregation/utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation creating build/bdist.linux-aarch64/wheel/sglang/srt/disaggregation/base copying build/lib/sglang/srt/disaggregation/base/conn.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/base copying build/lib/sglang/srt/disaggregation/base/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/base creating build/bdist.linux-aarch64/wheel/sglang/srt/disaggregation/nixl copying build/lib/sglang/srt/disaggregation/nixl/conn.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/nixl copying build/lib/sglang/srt/disaggregation/nixl/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation/nixl copying build/lib/sglang/srt/disaggregation/kv_events.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation copying build/lib/sglang/srt/disaggregation/decode.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/disaggregation creating build/bdist.linux-aarch64/wheel/sglang/srt/entrypoints copying build/lib/sglang/srt/entrypoints/EngineBase.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/entrypoints copying build/lib/sglang/srt/entrypoints/engine.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/entrypoints copying build/lib/sglang/srt/entrypoints/http_server.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/entrypoints copying build/lib/sglang/srt/entrypoints/http_server_engine.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/entrypoints copying build/lib/sglang/srt/entrypoints/verl_engine.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/entrypoints creating build/bdist.linux-aarch64/wheel/sglang/srt/speculative copying build/lib/sglang/srt/speculative/eagle_worker.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/speculative copying build/lib/sglang/srt/speculative/eagle_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/speculative copying build/lib/sglang/srt/speculative/eagle_draft_cuda_graph_runner.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/speculative copying build/lib/sglang/srt/speculative/build_eagle_tree.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/speculative copying build/lib/sglang/srt/speculative/spec_info.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/speculative creating build/bdist.linux-aarch64/wheel/sglang/srt/models copying build/lib/sglang/srt/models/gemma2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/mllama.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llama4.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/xverse.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/grok.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llama_classification.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen2_moe.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/yivl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llava.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/minicpmv.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/gemma2_reward.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/commandr.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/siglip.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/minicpm3.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llama_eagle.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llavavid.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/kimi_vl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/minicpmo.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/gpt2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/phi3_small.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/deepseek.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/exaone.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/gemma.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen3.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/olmo.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/internlm2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/xverse_moe.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen2_rm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/kimi_vl_moonvit.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/roberta.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/olmo2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/clip.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/deepseek_nextn.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/mixtral_quant.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/bert.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/mllama4.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/olmoe.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/internvl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/torch_native_llama.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/registry.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/internlm2_reward.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/mixtral.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/gemma3_mm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/mistral.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/gemma3_causal.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen2_5_vl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llama_embedding.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen2_vl.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/minicpm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/deepseek_v2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/mimo.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/deepseek_janus_pro.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/chatglm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen3_moe.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/baichuan.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen2_classification.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/dbrx.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llama.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llama_eagle3.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/llama_reward.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/gpt_bigcode.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/deepseek_vl2.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/pixtral.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/stablelm.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/mimo_mtp.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/qwen2_eagle.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models copying build/lib/sglang/srt/models/granite.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/models creating build/bdist.linux-aarch64/wheel/sglang/srt/openai_api copying build/lib/sglang/srt/openai_api/protocol.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/openai_api copying build/lib/sglang/srt/openai_api/adapter.py -> build/bdist.linux-aarch64/wheel/./sglang/srt/openai_api copying build/lib/sglang/bench_one_batch_server.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/utils.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/bench_offline_throughput.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/api.py -> build/bdist.linux-aarch64/wheel/./sglang copying build/lib/sglang/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang creating build/bdist.linux-aarch64/wheel/sglang/test copying build/lib/sglang/test/few_shot_gsm8k_engine.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/simple_eval_gpqa.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/simple_eval_math.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_dynamic_grad_mode.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/simple_eval_common.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_block_fp8_ep.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/simple_eval_humaneval.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_layernorm.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/few_shot_gsm8k.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_activation.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_block_fp8.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/runners.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_custom_ops.py -> build/bdist.linux-aarch64/wheel/./sglang/test creating build/bdist.linux-aarch64/wheel/sglang/test/attention copying build/lib/sglang/test/attention/test_flashattn_mla_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/test/attention copying build/lib/sglang/test/attention/test_prefix_chunk_info.py -> build/bdist.linux-aarch64/wheel/./sglang/test/attention copying build/lib/sglang/test/attention/test_flashattn_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/test/attention copying build/lib/sglang/test/attention/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/test/attention copying build/lib/sglang/test/test_deepep_utils.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/run_eval.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/send_one.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_cutlass_moe.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/simple_eval_mgsm.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/simple_eval_mmlu.py -> build/bdist.linux-aarch64/wheel/./sglang/test copying build/lib/sglang/test/test_programs.py -> build/bdist.linux-aarch64/wheel/./sglang/test creating build/bdist.linux-aarch64/wheel/sglang/eval copying build/lib/sglang/eval/llama3_eval.py -> build/bdist.linux-aarch64/wheel/./sglang/eval copying build/lib/sglang/eval/loogle_eval.py -> build/bdist.linux-aarch64/wheel/./sglang/eval creating build/bdist.linux-aarch64/wheel/sglang/lang copying build/lib/sglang/lang/chat_template.py -> build/bdist.linux-aarch64/wheel/./sglang/lang creating build/bdist.linux-aarch64/wheel/sglang/lang/backend copying build/lib/sglang/lang/backend/anthropic.py -> build/bdist.linux-aarch64/wheel/./sglang/lang/backend copying build/lib/sglang/lang/backend/base_backend.py -> build/bdist.linux-aarch64/wheel/./sglang/lang/backend copying build/lib/sglang/lang/backend/vertexai.py -> build/bdist.linux-aarch64/wheel/./sglang/lang/backend copying build/lib/sglang/lang/backend/litellm.py -> build/bdist.linux-aarch64/wheel/./sglang/lang/backend copying build/lib/sglang/lang/backend/runtime_endpoint.py -> build/bdist.linux-aarch64/wheel/./sglang/lang/backend copying build/lib/sglang/lang/backend/openai.py -> build/bdist.linux-aarch64/wheel/./sglang/lang/backend copying build/lib/sglang/lang/backend/__init__.py -> build/bdist.linux-aarch64/wheel/./sglang/lang/backend copying build/lib/sglang/lang/choices.py -> build/bdist.linux-aarch64/wheel/./sglang/lang copying build/lib/sglang/lang/interpreter.py -> build/bdist.linux-aarch64/wheel/./sglang/lang copying build/lib/sglang/lang/tracer.py -> build/bdist.linux-aarch64/wheel/./sglang/lang copying build/lib/sglang/lang/compiler.py -> build/bdist.linux-aarch64/wheel/./sglang/lang copying build/lib/sglang/lang/ir.py -> build/bdist.linux-aarch64/wheel/./sglang/lang copying build/lib/sglang/global_config.py -> build/bdist.linux-aarch64/wheel/./sglang running install_egg_info Copying sglang.egg-info to build/bdist.linux-aarch64/wheel/./sglang-0.4.6.post5-py3.11.egg-info running install_scripts creating build/bdist.linux-aarch64/wheel/sglang-0.4.6.post5.dist-info/WHEEL creating '/tmp/pip-wheel-b1unl85n/.tmp-27vlmxnq/sglang-0.4.6.post5-py3-none-any.whl' and adding 'build/bdist.linux-aarch64/wheel' to it adding 'sglang/__init__.py' adding 'sglang/api.py' adding 'sglang/bench_offline_throughput.py' adding 'sglang/bench_one_batch.py' adding 'sglang/bench_one_batch_server.py' adding 'sglang/bench_serving.py' adding 'sglang/check_env.py' adding 'sglang/compile_deep_gemm.py' adding 'sglang/global_config.py' adding 'sglang/launch_server.py' adding 'sglang/utils.py' adding 'sglang/version.py' adding 'sglang/eval/llama3_eval.py' adding 'sglang/eval/loogle_eval.py' adding 'sglang/lang/chat_template.py' adding 'sglang/lang/choices.py' adding 'sglang/lang/compiler.py' adding 'sglang/lang/interpreter.py' adding 'sglang/lang/ir.py' adding 'sglang/lang/tracer.py' adding 'sglang/lang/backend/__init__.py' adding 'sglang/lang/backend/anthropic.py' adding 'sglang/lang/backend/base_backend.py' adding 'sglang/lang/backend/litellm.py' adding 'sglang/lang/backend/openai.py' adding 'sglang/lang/backend/runtime_endpoint.py' adding 'sglang/lang/backend/vertexai.py' adding 'sglang/srt/_custom_ops.py' adding 'sglang/srt/aio_rwlock.py' adding 'sglang/srt/code_completion_parser.py' adding 'sglang/srt/conversation.py' adding 'sglang/srt/custom_op.py' adding 'sglang/srt/hf_transformers_utils.py' adding 'sglang/srt/mm_utils.py' adding 'sglang/srt/model_parallel.py' adding 'sglang/srt/operations.py' adding 'sglang/srt/operations_strategy.py' adding 'sglang/srt/patch_torch.py' adding 'sglang/srt/reasoning_parser.py' adding 'sglang/srt/server_args.py' adding 'sglang/srt/torch_memory_saver_adapter.py' adding 'sglang/srt/utils.py' adding 'sglang/srt/warmup.py' adding 'sglang/srt/configs/__init__.py' adding 'sglang/srt/configs/chatglm.py' adding 'sglang/srt/configs/dbrx.py' adding 'sglang/srt/configs/deepseekvl2.py' adding 'sglang/srt/configs/device_config.py' adding 'sglang/srt/configs/exaone.py' adding 'sglang/srt/configs/internvl.py' adding 'sglang/srt/configs/janus_pro.py' adding 'sglang/srt/configs/kimi_vl.py' adding 'sglang/srt/configs/kimi_vl_moonvit.py' adding 'sglang/srt/configs/load_config.py' adding 'sglang/srt/configs/model_config.py' adding 'sglang/srt/configs/utils.py' adding 'sglang/srt/connector/__init__.py' adding 'sglang/srt/connector/base_connector.py' adding 'sglang/srt/connector/redis.py' adding 'sglang/srt/connector/s3.py' adding 'sglang/srt/connector/utils.py' adding 'sglang/srt/connector/serde/__init__.py' adding 'sglang/srt/connector/serde/safe_serde.py' adding 'sglang/srt/connector/serde/serde.py' adding 'sglang/srt/constrained/base_grammar_backend.py' adding 'sglang/srt/constrained/llguidance_backend.py' adding 'sglang/srt/constrained/outlines_backend.py' adding 'sglang/srt/constrained/outlines_jump_forward.py' adding 'sglang/srt/constrained/reasoner_grammar_backend.py' adding 'sglang/srt/constrained/xgrammar_backend.py' adding 'sglang/srt/constrained/triton_ops/bitmask_ops.py' adding 'sglang/srt/disaggregation/decode.py' adding 'sglang/srt/disaggregation/decode_schedule_batch_mixin.py' adding 'sglang/srt/disaggregation/kv_events.py' adding 'sglang/srt/disaggregation/mini_lb.py' adding 'sglang/srt/disaggregation/prefill.py' adding 'sglang/srt/disaggregation/utils.py' adding 'sglang/srt/disaggregation/base/__init__.py' adding 'sglang/srt/disaggregation/base/conn.py' adding 'sglang/srt/disaggregation/fake/__init__.py' adding 'sglang/srt/disaggregation/fake/conn.py' adding 'sglang/srt/disaggregation/mooncake/__init__.py' adding 'sglang/srt/disaggregation/mooncake/conn.py' adding 'sglang/srt/disaggregation/mooncake/transfer_engine.py' adding 'sglang/srt/disaggregation/nixl/__init__.py' adding 'sglang/srt/disaggregation/nixl/conn.py' adding 'sglang/srt/distributed/__init__.py' adding 'sglang/srt/distributed/communication_op.py' adding 'sglang/srt/distributed/parallel_state.py' adding 'sglang/srt/distributed/utils.py' adding 'sglang/srt/distributed/device_communicators/cuda_wrapper.py' adding 'sglang/srt/distributed/device_communicators/custom_all_reduce.py' adding 'sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py' adding 'sglang/srt/distributed/device_communicators/hpu_communicator.py' adding 'sglang/srt/distributed/device_communicators/npu_communicator.py' adding 'sglang/srt/distributed/device_communicators/pynccl.py' adding 'sglang/srt/distributed/device_communicators/pynccl_wrapper.py' adding 'sglang/srt/distributed/device_communicators/shm_broadcast.py' adding 'sglang/srt/distributed/device_communicators/xpu_communicator.py' adding 'sglang/srt/entrypoints/EngineBase.py' adding 'sglang/srt/entrypoints/engine.py' adding 'sglang/srt/entrypoints/http_server.py' adding 'sglang/srt/entrypoints/http_server_engine.py' adding 'sglang/srt/entrypoints/verl_engine.py' adding 'sglang/srt/function_call/base_format_detector.py' adding 'sglang/srt/function_call/core_types.py' adding 'sglang/srt/function_call/deepseekv3_detector.py' adding 'sglang/srt/function_call/ebnf_composer.py' adding 'sglang/srt/function_call/function_call_parser.py' adding 'sglang/srt/function_call/llama32_detector.py' adding 'sglang/srt/function_call/mistral_detector.py' adding 'sglang/srt/function_call/pythonic_detector.py' adding 'sglang/srt/function_call/qwen25_detector.py' adding 'sglang/srt/function_call/utils.py' adding 'sglang/srt/layers/activation.py' adding 'sglang/srt/layers/communicator.py' adding 'sglang/srt/layers/dp_attention.py' adding 'sglang/srt/layers/elementwise.py' adding 'sglang/srt/layers/layernorm.py' adding 'sglang/srt/layers/linear.py' adding 'sglang/srt/layers/logits_processor.py' adding 'sglang/srt/layers/multimodal.py' adding 'sglang/srt/layers/parameter.py' adding 'sglang/srt/layers/pooler.py' adding 'sglang/srt/layers/radix_attention.py' adding 'sglang/srt/layers/rotary_embedding.py' adding 'sglang/srt/layers/sampler.py' adding 'sglang/srt/layers/torchao_utils.py' adding 'sglang/srt/layers/utils.py' adding 'sglang/srt/layers/vocab_parallel_embedding.py' adding 'sglang/srt/layers/attention/aiter_backend.py' adding 'sglang/srt/layers/attention/base_attn_backend.py' adding 'sglang/srt/layers/attention/cutlass_mla_backend.py' adding 'sglang/srt/layers/attention/double_sparsity_backend.py' adding 'sglang/srt/layers/attention/flashattention_backend.py' adding 'sglang/srt/layers/attention/flashinfer_backend.py' adding 'sglang/srt/layers/attention/flashinfer_mla_backend.py' adding 'sglang/srt/layers/attention/flashmla_backend.py' adding 'sglang/srt/layers/attention/merge_state.py' adding 'sglang/srt/layers/attention/torch_native_backend.py' adding 'sglang/srt/layers/attention/triton_backend.py' adding 'sglang/srt/layers/attention/utils.py' adding 'sglang/srt/layers/attention/vision.py' adding 'sglang/srt/layers/attention/triton_ops/decode_attention.py' adding 'sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py' adding 'sglang/srt/layers/attention/triton_ops/extend_attention.py' adding 'sglang/srt/layers/attention/triton_ops/merge_state.py' adding 'sglang/srt/layers/attention/triton_ops/prefill_attention.py' adding 'sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py' adding 'sglang/srt/layers/moe/cutlass_moe.py' adding 'sglang/srt/layers/moe/fused_moe_native.py' adding 'sglang/srt/layers/moe/router.py' adding 'sglang/srt/layers/moe/topk.py' adding 'sglang/srt/layers/moe/ep_moe/__init__.py' adding 'sglang/srt/layers/moe/ep_moe/kernels.py' adding 'sglang/srt/layers/moe/ep_moe/layer.py' adding 'sglang/srt/layers/moe/ep_moe/token_dispatcher.py' adding 'sglang/srt/layers/moe/fused_moe_triton/__init__.py' adding 'sglang/srt/layers/moe/fused_moe_triton/fused_moe.py' adding 'sglang/srt/layers/moe/fused_moe_triton/layer.py' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H20.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=96,device_name=NVIDIA_H20.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Radeon_Graphics.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Radeon_Graphics.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Radeon_Graphics.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_L40S.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Radeon_Graphics.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json' adding 'sglang/srt/layers/quantization/__init__.py' adding 'sglang/srt/layers/quantization/awq.py' adding 'sglang/srt/layers/quantization/base_config.py' adding 'sglang/srt/layers/quantization/blockwise_int8.py' adding 'sglang/srt/layers/quantization/deep_gemm.py' adding 'sglang/srt/layers/quantization/fp8.py' adding 'sglang/srt/layers/quantization/fp8_kernel.py' adding 'sglang/srt/layers/quantization/fp8_utils.py' adding 'sglang/srt/layers/quantization/gptq.py' adding 'sglang/srt/layers/quantization/int8_kernel.py' adding 'sglang/srt/layers/quantization/int8_utils.py' adding 'sglang/srt/layers/quantization/kv_cache.py' adding 'sglang/srt/layers/quantization/modelopt_quant.py' adding 'sglang/srt/layers/quantization/moe_wna16.py' adding 'sglang/srt/layers/quantization/qoq.py' adding 'sglang/srt/layers/quantization/utils.py' adding 'sglang/srt/layers/quantization/w8a8_fp8.py' adding 'sglang/srt/layers/quantization/w8a8_int8.py' adding 'sglang/srt/layers/quantization/compressed_tensors/__init__.py' adding 'sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py' adding 'sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py' adding 'sglang/srt/layers/quantization/compressed_tensors/utils.py' adding 'sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py' adding 'sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py' adding 'sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py' adding 'sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py' adding 'sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json' adding 'sglang/srt/lora/layers.py' adding 'sglang/srt/lora/lora.py' adding 'sglang/srt/lora/lora_config.py' adding 'sglang/srt/lora/lora_manager.py' adding 'sglang/srt/lora/mem_pool.py' adding 'sglang/srt/lora/utils.py' adding 'sglang/srt/lora/backend/base_backend.py' adding 'sglang/srt/lora/backend/flashinfer_backend.py' adding 'sglang/srt/lora/backend/triton_backend.py' adding 'sglang/srt/lora/triton_ops/__init__.py' adding 'sglang/srt/lora/triton_ops/gate_up_lora_b.py' adding 'sglang/srt/lora/triton_ops/qkv_lora_b.py' adding 'sglang/srt/lora/triton_ops/sgemm_lora_a.py' adding 'sglang/srt/lora/triton_ops/sgemm_lora_b.py' adding 'sglang/srt/managers/cache_controller.py' adding 'sglang/srt/managers/configure_logging.py' adding 'sglang/srt/managers/data_parallel_controller.py' adding 'sglang/srt/managers/deepseek_eplb.py' adding 'sglang/srt/managers/detokenizer_manager.py' adding 'sglang/srt/managers/eplb_manager.py' adding 'sglang/srt/managers/expert_distribution.py' adding 'sglang/srt/managers/expert_location.py' adding 'sglang/srt/managers/expert_location_dispatch.py' adding 'sglang/srt/managers/io_struct.py' adding 'sglang/srt/managers/mm_utils.py' adding 'sglang/srt/managers/multimodal_processor.py' adding 'sglang/srt/managers/schedule_batch.py' adding 'sglang/srt/managers/schedule_policy.py' adding 'sglang/srt/managers/scheduler.py' adding 'sglang/srt/managers/scheduler_output_processor_mixin.py' adding 'sglang/srt/managers/session_controller.py' adding 'sglang/srt/managers/tokenizer_manager.py' adding 'sglang/srt/managers/tp_worker.py' adding 'sglang/srt/managers/tp_worker_overlap_thread.py' adding 'sglang/srt/managers/utils.py' adding 'sglang/srt/managers/multimodal_processors/base_processor.py' adding 'sglang/srt/managers/multimodal_processors/clip.py' adding 'sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py' adding 'sglang/srt/managers/multimodal_processors/gemma3.py' adding 'sglang/srt/managers/multimodal_processors/internvl.py' adding 'sglang/srt/managers/multimodal_processors/janus_pro.py' adding 'sglang/srt/managers/multimodal_processors/kimi_vl.py' adding 'sglang/srt/managers/multimodal_processors/llava.py' adding 'sglang/srt/managers/multimodal_processors/minicpm.py' adding 'sglang/srt/managers/multimodal_processors/mlama.py' adding 'sglang/srt/managers/multimodal_processors/mllama4.py' adding 'sglang/srt/managers/multimodal_processors/pixtral.py' adding 'sglang/srt/managers/multimodal_processors/qwen_vl.py' adding 'sglang/srt/mem_cache/base_prefix_cache.py' adding 'sglang/srt/mem_cache/chunk_cache.py' adding 'sglang/srt/mem_cache/flush_cache.py' adding 'sglang/srt/mem_cache/hiradix_cache.py' adding 'sglang/srt/mem_cache/memory_pool.py' adding 'sglang/srt/mem_cache/multimodal_cache.py' adding 'sglang/srt/mem_cache/paged_allocator.py' adding 'sglang/srt/mem_cache/radix_cache.py' adding 'sglang/srt/metrics/collector.py' adding 'sglang/srt/metrics/func_timer.py' adding 'sglang/srt/model_executor/cuda_graph_runner.py' adding 'sglang/srt/model_executor/expert_location_updater.py' adding 'sglang/srt/model_executor/forward_batch_info.py' adding 'sglang/srt/model_executor/model_runner.py' adding 'sglang/srt/model_loader/__init__.py' adding 'sglang/srt/model_loader/loader.py' adding 'sglang/srt/model_loader/utils.py' adding 'sglang/srt/model_loader/weight_utils.py' adding 'sglang/srt/models/baichuan.py' adding 'sglang/srt/models/bert.py' adding 'sglang/srt/models/chatglm.py' adding 'sglang/srt/models/clip.py' adding 'sglang/srt/models/commandr.py' adding 'sglang/srt/models/dbrx.py' adding 'sglang/srt/models/deepseek.py' adding 'sglang/srt/models/deepseek_janus_pro.py' adding 'sglang/srt/models/deepseek_nextn.py' adding 'sglang/srt/models/deepseek_v2.py' adding 'sglang/srt/models/deepseek_vl2.py' adding 'sglang/srt/models/exaone.py' adding 'sglang/srt/models/gemma.py' adding 'sglang/srt/models/gemma2.py' adding 'sglang/srt/models/gemma2_reward.py' adding 'sglang/srt/models/gemma3_causal.py' adding 'sglang/srt/models/gemma3_mm.py' adding 'sglang/srt/models/gpt2.py' adding 'sglang/srt/models/gpt_bigcode.py' adding 'sglang/srt/models/granite.py' adding 'sglang/srt/models/grok.py' adding 'sglang/srt/models/internlm2.py' adding 'sglang/srt/models/internlm2_reward.py' adding 'sglang/srt/models/internvl.py' adding 'sglang/srt/models/kimi_vl.py' adding 'sglang/srt/models/kimi_vl_moonvit.py' adding 'sglang/srt/models/llama.py' adding 'sglang/srt/models/llama4.py' adding 'sglang/srt/models/llama_classification.py' adding 'sglang/srt/models/llama_eagle.py' adding 'sglang/srt/models/llama_eagle3.py' adding 'sglang/srt/models/llama_embedding.py' adding 'sglang/srt/models/llama_reward.py' adding 'sglang/srt/models/llava.py' adding 'sglang/srt/models/llavavid.py' adding 'sglang/srt/models/mimo.py' adding 'sglang/srt/models/mimo_mtp.py' adding 'sglang/srt/models/minicpm.py' adding 'sglang/srt/models/minicpm3.py' adding 'sglang/srt/models/minicpmo.py' adding 'sglang/srt/models/minicpmv.py' adding 'sglang/srt/models/mistral.py' adding 'sglang/srt/models/mixtral.py' adding 'sglang/srt/models/mixtral_quant.py' adding 'sglang/srt/models/mllama.py' adding 'sglang/srt/models/mllama4.py' adding 'sglang/srt/models/olmo.py' adding 'sglang/srt/models/olmo2.py' adding 'sglang/srt/models/olmoe.py' adding 'sglang/srt/models/phi3_small.py' adding 'sglang/srt/models/pixtral.py' adding 'sglang/srt/models/qwen.py' adding 'sglang/srt/models/qwen2.py' adding 'sglang/srt/models/qwen2_5_vl.py' adding 'sglang/srt/models/qwen2_classification.py' adding 'sglang/srt/models/qwen2_eagle.py' adding 'sglang/srt/models/qwen2_moe.py' adding 'sglang/srt/models/qwen2_rm.py' adding 'sglang/srt/models/qwen2_vl.py' adding 'sglang/srt/models/qwen3.py' adding 'sglang/srt/models/qwen3_moe.py' adding 'sglang/srt/models/registry.py' adding 'sglang/srt/models/roberta.py' adding 'sglang/srt/models/siglip.py' adding 'sglang/srt/models/stablelm.py' adding 'sglang/srt/models/torch_native_llama.py' adding 'sglang/srt/models/xverse.py' adding 'sglang/srt/models/xverse_moe.py' adding 'sglang/srt/models/yivl.py' adding 'sglang/srt/openai_api/adapter.py' adding 'sglang/srt/openai_api/protocol.py' adding 'sglang/srt/sampling/custom_logit_processor.py' adding 'sglang/srt/sampling/sampling_batch_info.py' adding 'sglang/srt/sampling/sampling_params.py' adding 'sglang/srt/sampling/penaltylib/__init__.py' adding 'sglang/srt/sampling/penaltylib/frequency_penalty.py' adding 'sglang/srt/sampling/penaltylib/min_new_tokens.py' adding 'sglang/srt/sampling/penaltylib/orchestrator.py' adding 'sglang/srt/sampling/penaltylib/presence_penalty.py' adding 'sglang/srt/speculative/build_eagle_tree.py' adding 'sglang/srt/speculative/eagle_draft_cuda_graph_runner.py' adding 'sglang/srt/speculative/eagle_utils.py' adding 'sglang/srt/speculative/eagle_worker.py' adding 'sglang/srt/speculative/spec_info.py' adding 'sglang/test/__init__.py' adding 'sglang/test/few_shot_gsm8k.py' adding 'sglang/test/few_shot_gsm8k_engine.py' adding 'sglang/test/run_eval.py' adding 'sglang/test/runners.py' adding 'sglang/test/send_one.py' adding 'sglang/test/simple_eval_common.py' adding 'sglang/test/simple_eval_gpqa.py' adding 'sglang/test/simple_eval_humaneval.py' adding 'sglang/test/simple_eval_math.py' adding 'sglang/test/simple_eval_mgsm.py' adding 'sglang/test/simple_eval_mmlu.py' adding 'sglang/test/test_activation.py' adding 'sglang/test/test_block_fp8.py' adding 'sglang/test/test_block_fp8_ep.py' adding 'sglang/test/test_custom_ops.py' adding 'sglang/test/test_cutlass_moe.py' adding 'sglang/test/test_deepep_utils.py' adding 'sglang/test/test_dynamic_grad_mode.py' adding 'sglang/test/test_layernorm.py' adding 'sglang/test/test_programs.py' adding 'sglang/test/test_utils.py' adding 'sglang/test/attention/__init__.py' adding 'sglang/test/attention/test_flashattn_backend.py' adding 'sglang/test/attention/test_flashattn_mla_backend.py' adding 'sglang/test/attention/test_prefix_chunk_info.py' adding 'sglang-0.4.6.post5.dist-info/licenses/LICENSE' adding 'sglang-0.4.6.post5.dist-info/METADATA' adding 'sglang-0.4.6.post5.dist-info/WHEEL' adding 'sglang-0.4.6.post5.dist-info/top_level.txt' adding 'sglang-0.4.6.post5.dist-info/RECORD' removing build/bdist.linux-aarch64/wheel Building wheel for sglang (pyproject.toml): finished with status 'done' Created wheel for sglang: filename=sglang-0.4.6.post5-py3-none-any.whl size=1393681 sha256=a3083854e23f9fdacfa935ec11bafd69533de1d197a9f82347ace0204078e180 Stored in directory: /builddir/.cache/pip/wheels/54/d9/ff/955066274737426bf0d2c026e8a501f53024566a24df90314e Successfully built sglang + sleep 1 + RPM_EC=0 ++ jobs -p + exit 0 Executing(%install): /bin/sh -e /var/tmp/rpm-tmp.dxA4yK + umask 022 + cd /builddir/build/BUILD + '[' /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 '!=' / ']' + rm -rf /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 ++ dirname /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 + mkdir -p /builddir/build/BUILDROOT + mkdir /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 + export AM_UPDATE_INFO_DIR=no + AM_UPDATE_INFO_DIR=no + cd sglang-0.4.6.post5 ++ ls ./build/sglang-0.4.6.post5-py3-none-any.whl ++ xargs basename --multiple ++ sed -E 's/([^-]+)-([^-]+)-.+\.whl/\1==\2/' + specifier=sglang==0.4.6.post5 + CFLAGS='-O2 -flto=auto -ffat-lto-objects -g -grecord-gcc-switches -pipe -fstack-protector-strong -Wall -Werror=format-security -Wp,-U_FORTIFY_SOURCE,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -specs=/usr/lib/rpm/generic-hardened-cc1 -mbranch-protection=standard -fasynchronous-unwind-tables -fstack-clash-protection' + LDFLAGS='-Wl,-z,relro -Wl,--as-needed -Wl,-z,now -specs=/usr/lib/rpm/generic-hardened-ld -specs=/usr/lib/rpm/openEuler/openEuler-package-notes' + /usr/bin/python3 -mpip install --verbose --progress-bar off --disable-pip-version-check --root /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 --no-compile --ignore-installed --no-deps --no-index --find-links ./build sglang==0.4.6.post5 Using pip 23.3.1 from /usr/lib/python3.11/site-packages/pip (python 3.11) Looking in links: ./build Processing ./build/sglang-0.4.6.post5-py3-none-any.whl Installing collected packages: sglang Successfully installed sglang-0.4.6.post5 + install -d -m755 /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64//usr/share/doc/python-sglang + '[' -d doc ']' ~/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 ~/build/BUILD/sglang-0.4.6.post5 + '[' -d docs ']' + '[' -d example ']' + '[' -d examples ']' + pushd /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 + touch filelist.lst + '[' -d usr/lib64 ']' + '[' -d usr/bin ']' + '[' -d usr/sbin ']' + touch doclist.lst ~/build/BUILD/sglang-0.4.6.post5 + '[' -d usr/share/man ']' + popd + mv /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64/filelist.lst . + mv /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64/doclist.lst . + /usr/bin/find-debuginfo -j4 --strict-build-id -i --build-id-seed 0.4.6.post5-2 --unique-debug-suffix -0.4.6.post5-2.aarch64 --unique-debug-src-base python-sglang-0.4.6.post5-2.aarch64 -S debugsourcefiles.list /builddir/build/BUILD/sglang-0.4.6.post5 find-debuginfo: starting Extracting debug info from 0 files Creating .debug symlinks for symlinks to ELF files find: 'debug': No such file or directory find-debuginfo: done + /usr/lib/rpm/check-buildroot + /usr/lib/rpm/brp-ldconfig + /usr/lib/rpm/brp-compress + /usr/lib/rpm/brp-strip-lto /usr/bin/strip + /usr/lib/rpm/brp-strip-static-archive /usr/bin/strip + /usr/lib/rpm/brp-check-elf-files + /usr/lib/rpm/brp-remove-la-files + /usr/lib/rpm/brp-remove-info-dir + /usr/lib/rpm/brp-clean-perl-files + /usr/lib/rpm/brp-python-bytecompile /usr/bin/python3 1 0 Bytecompiling .py files below /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64/usr/lib/python3.11 using /usr/bin/python3.11 + /usr/lib/rpm/brp-python-hardlink Processing files: python3-sglang-0.4.6.post5-2.noarch warning: Empty %files file /builddir/build/BUILD/sglang-0.4.6.post5/filelist.lst Provides: python-sglang python3-sglang = 0.4.6.post5-2 python3.11dist(sglang) = 0.4.6^post5 python3dist(sglang) = 0.4.6^post5 Requires(rpmlib): rpmlib(CompressedFileNames) <= 3.0.4-1 rpmlib(FileDigests) <= 4.6.0-1 rpmlib(PartialHardlinkSets) <= 4.0.4-1 rpmlib(PayloadFilesHavePrefix) <= 4.0-1 Requires: python(abi) = 3.11 python3.11dist(aiohttp) python3.11dist(ipython) python3.11dist(numpy) python3.11dist(requests) python3.11dist(setproctitle) python3.11dist(tqdm) Checking for unpackaged file(s): /usr/lib/rpm/check-files /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 Wrote: /builddir/build/RPMS/python3-sglang-0.4.6.post5-2.noarch.rpm Executing(%clean): /bin/sh -e /var/tmp/rpm-tmp.z2SiK9 + umask 022 + cd /builddir/build/BUILD + cd sglang-0.4.6.post5 + /usr/bin/rm -rf /builddir/build/BUILDROOT/python-sglang-0.4.6.post5-2.aarch64 + RPM_EC=0 ++ jobs -p + exit 0 Executing(rmbuild): /bin/sh -e /var/tmp/rpm-tmp.pRMOjC + umask 022 + cd /builddir/build/BUILD + rm -rf sglang-0.4.6.post5 sglang-0.4.6.post5.gemspec + RPM_EC=0 ++ jobs -p + exit 0 RPM build warnings: Empty %files file /builddir/build/BUILD/sglang-0.4.6.post5/filelist.lst Child return code was: 0