1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
|
%global _empty_manifest_terminate_build 0
Name: python-torchelastic
Version: 0.2.2
Release: 1
Summary: PyTorch Elastic Training
License: BSD-3
URL: https://github.com/pytorch/elastic
Source0: https://mirrors.aliyun.com/pypi/web/packages/4f/b5/6b598fe8881a2de40e5a01100ab5932c8b791b9249ccc99c0d5006443c93/torchelastic-0.2.2.tar.gz
BuildArch: noarch
Requires: python3-numpy
Requires: python3-etcd
Requires: python3-torch
%description
[](LICENSE)[](https://circleci.com/gh/pytorch/elastic)
# TorchElastic
TorchElastic allows you to launch distributed PyTorch jobs in a
fault-tolerant and elastic manner.
For the latest documentation, please refer to our
[website](https://pytorch.org/elastic).
## Requirements
torchelastic requires
* python3 (3.8+)
* torch
* etcd
## Installation
```bash
pip install torchelastic
```
## Quickstart
**Fault-tolerant** on `4` nodes, `8` trainers/node, total `4 * 8 = 32` trainers.
Run the following on all nodes.
```bash
python -m torchelastic.distributed.launch
--nnodes=4
--nproc_per_node=8
--rdzv_id=JOB_ID
--rdzv_backend=etcd
--rdzv_endpoint=ETCD_HOST:ETCD_PORT
YOUR_TRAINING_SCRIPT.py (--arg1 ... train script args...)
```
**Elastic on** `1 ~ 4` nodes, `8` trainers/node, total `8 ~ 32` trainers. Job
starts as soon as `1` node is healthy, you may add up to `4` nodes.
```bash
python -m torchelastic.distributed.launch
--nnodes=1:4
--nproc_per_node=8
--rdzv_id=JOB_ID
--rdzv_backend=etcd
--rdzv_endpoint=ETCD_HOST:ETCD_PORT
YOUR_TRAINING_SCRIPT.py (--arg1 ... train script args...)
```
## Contributing
We welcome PRs. See the [CONTRIBUTING](CONTRIBUTING.md) file.
## License
torchelastic is BSD licensed, as found in the [LICENSE](LICENSE) file.
%package -n python3-torchelastic
Summary: PyTorch Elastic Training
Provides: python-torchelastic
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-torchelastic
[](LICENSE)[](https://circleci.com/gh/pytorch/elastic)
# TorchElastic
TorchElastic allows you to launch distributed PyTorch jobs in a
fault-tolerant and elastic manner.
For the latest documentation, please refer to our
[website](https://pytorch.org/elastic).
## Requirements
torchelastic requires
* python3 (3.8+)
* torch
* etcd
## Installation
```bash
pip install torchelastic
```
## Quickstart
**Fault-tolerant** on `4` nodes, `8` trainers/node, total `4 * 8 = 32` trainers.
Run the following on all nodes.
```bash
python -m torchelastic.distributed.launch
--nnodes=4
--nproc_per_node=8
--rdzv_id=JOB_ID
--rdzv_backend=etcd
--rdzv_endpoint=ETCD_HOST:ETCD_PORT
YOUR_TRAINING_SCRIPT.py (--arg1 ... train script args...)
```
**Elastic on** `1 ~ 4` nodes, `8` trainers/node, total `8 ~ 32` trainers. Job
starts as soon as `1` node is healthy, you may add up to `4` nodes.
```bash
python -m torchelastic.distributed.launch
--nnodes=1:4
--nproc_per_node=8
--rdzv_id=JOB_ID
--rdzv_backend=etcd
--rdzv_endpoint=ETCD_HOST:ETCD_PORT
YOUR_TRAINING_SCRIPT.py (--arg1 ... train script args...)
```
## Contributing
We welcome PRs. See the [CONTRIBUTING](CONTRIBUTING.md) file.
## License
torchelastic is BSD licensed, as found in the [LICENSE](LICENSE) file.
%package help
Summary: Development documents and examples for torchelastic
Provides: python3-torchelastic-doc
%description help
[](LICENSE)[](https://circleci.com/gh/pytorch/elastic)
# TorchElastic
TorchElastic allows you to launch distributed PyTorch jobs in a
fault-tolerant and elastic manner.
For the latest documentation, please refer to our
[website](https://pytorch.org/elastic).
## Requirements
torchelastic requires
* python3 (3.8+)
* torch
* etcd
## Installation
```bash
pip install torchelastic
```
## Quickstart
**Fault-tolerant** on `4` nodes, `8` trainers/node, total `4 * 8 = 32` trainers.
Run the following on all nodes.
```bash
python -m torchelastic.distributed.launch
--nnodes=4
--nproc_per_node=8
--rdzv_id=JOB_ID
--rdzv_backend=etcd
--rdzv_endpoint=ETCD_HOST:ETCD_PORT
YOUR_TRAINING_SCRIPT.py (--arg1 ... train script args...)
```
**Elastic on** `1 ~ 4` nodes, `8` trainers/node, total `8 ~ 32` trainers. Job
starts as soon as `1` node is healthy, you may add up to `4` nodes.
```bash
python -m torchelastic.distributed.launch
--nnodes=1:4
--nproc_per_node=8
--rdzv_id=JOB_ID
--rdzv_backend=etcd
--rdzv_endpoint=ETCD_HOST:ETCD_PORT
YOUR_TRAINING_SCRIPT.py (--arg1 ... train script args...)
```
## Contributing
We welcome PRs. See the [CONTRIBUTING](CONTRIBUTING.md) file.
## License
torchelastic is BSD licensed, as found in the [LICENSE](LICENSE) file.
%prep
%autosetup -n torchelastic-0.2.2
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "\"/%h/%f.gz\"\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-torchelastic -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Thu Jun 08 2023 Python_Bot <Python_Bot@openeuler.org> - 0.2.2-1
- Package Spec generated
|
