-
Notifications
You must be signed in to change notification settings - Fork 321
227 lines (202 loc) · 7.37 KB
/
test-linux.yml
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
name: Unit-tests on Linux
on:
pull_request:
push:
branches:
- nightly
- main
- release/*
workflow_dispatch:
env:
CHANNEL: "nightly"
concurrency:
# Documentation suggests ${{ github.head_ref }}, but that's only available on pull_request/pull_request_target triggers, so using ${{ github.ref }}.
# On master, we want all builds to complete even if merging happens faster to make it easier to discover at which point something broke.
group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && format('ci-master-{0}', github.sha) || format('ci-{0}', github.ref) }}
cancel-in-progress: true
jobs:
tests-cpu:
strategy:
matrix:
python_version: ["3.9", "3.10", "3.11", "3.12"]
fail-fast: false
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.12xlarge
repository: pytorch/rl
docker-image: "nvidia/cuda:12.2.0-devel-ubuntu22.04"
timeout: 90
script: |
if [[ "${{ github.ref }}" =~ release/* ]]; then
export RELEASE=1
export TORCH_VERSION=stable
else
export RELEASE=0
export TORCH_VERSION=nightly
fi
export TD_GET_DEFAULTS_TO_NONE=1
# Set env vars from matrix
export PYTHON_VERSION=${{ matrix.python_version }}
export CU_VERSION="cpu"
echo "PYTHON_VERSION: $PYTHON_VERSION"
echo "CU_VERSION: $CU_VERSION"
## setup_env.sh
bash .github/unittest/linux/scripts/run_all.sh
tests-cpu-oldget:
# Tests that TD_GET_DEFAULTS_TO_NONE=0 works fine as this will be the default for TD up to 0.7
strategy:
matrix:
python_version: ["3.12"]
fail-fast: false
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.12xlarge
repository: pytorch/rl
docker-image: "nvidia/cuda:12.2.0-devel-ubuntu22.04"
timeout: 90
script: |
if [[ "${{ github.ref }}" =~ release/* ]]; then
export RELEASE=1
export TORCH_VERSION=stable
else
export RELEASE=0
export TORCH_VERSION=nightly
fi
export TD_GET_DEFAULTS_TO_NONE=0
# Set env vars from matrix
export PYTHON_VERSION=${{ matrix.python_version }}
export CU_VERSION="cpu"
echo "PYTHON_VERSION: $PYTHON_VERSION"
echo "CU_VERSION: $CU_VERSION"
## setup_env.sh
bash .github/unittest/linux/scripts/run_all.sh
tests-gpu:
strategy:
matrix:
python_version: ["3.11"]
cuda_arch_version: ["12.1"]
fail-fast: false
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.g5.4xlarge.nvidia.gpu
repository: pytorch/rl
docker-image: "nvidia/cuda:12.1.0-devel-ubuntu22.04"
gpu-arch-type: cuda
gpu-arch-version: ${{ matrix.cuda_arch_version }}
timeout: 90
script: |
# Set env vars from matrix
export PYTHON_VERSION=${{ matrix.python_version }}
# Commenting these out for now because the GPU test are not working inside docker
export CUDA_ARCH_VERSION=${{ matrix.cuda_arch_version }}
export CU_VERSION="cu${CUDA_ARCH_VERSION:0:2}${CUDA_ARCH_VERSION:3:1}"
if [[ "${{ github.ref }}" =~ release/* ]]; then
export RELEASE=1
export TORCH_VERSION=stable
else
export RELEASE=0
export TORCH_VERSION=nightly
fi
export TD_GET_DEFAULTS_TO_NONE=1
# Remove the following line when the GPU tests are working inside docker, and uncomment the above lines
#export CU_VERSION="cpu"
echo "PYTHON_VERSION: $PYTHON_VERSION"
echo "CU_VERSION: $CU_VERSION"
## setup_env.sh
bash .github/unittest/linux/scripts/run_all.sh
tests-olddeps:
strategy:
matrix:
python_version: ["3.8"]
cuda_arch_version: ["11.6"]
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
repository: pytorch/rl
runner: "linux.g5.4xlarge.nvidia.gpu"
# gpu-arch-type: cuda
# gpu-arch-version: "11.7"
docker-image: "nvidia/cudagl:11.4.0-base"
timeout: 120
script: |
set -euo pipefail
export PYTHON_VERSION="3.9"
export CU_VERSION="cu116"
export TAR_OPTIONS="--no-same-owner"
if [[ "${{ github.ref }}" =~ release/* ]]; then
export RELEASE=1
export TORCH_VERSION=stable
else
export RELEASE=0
export TORCH_VERSION=nightly
fi
export TF_CPP_MIN_LOG_LEVEL=0
export TD_GET_DEFAULTS_TO_NONE=1
bash .github/unittest/linux_olddeps/scripts_gym_0_13/setup_env.sh
bash .github/unittest/linux_olddeps/scripts_gym_0_13/batch_scripts.sh
bash .github/unittest/linux_olddeps/scripts_gym_0_13/post_process.sh
tests-optdeps:
strategy:
matrix:
python_version: ["3.11"]
cuda_arch_version: ["12.1"]
fail-fast: false
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.g5.4xlarge.nvidia.gpu
repository: pytorch/rl
docker-image: "nvidia/cuda:12.1.0-devel-ubuntu22.04"
gpu-arch-type: cuda
gpu-arch-version: ${{ matrix.cuda_arch_version }}
timeout: 90
script: |
# Set env vars from matrix
export PYTHON_VERSION=${{ matrix.python_version }}
# Commenting these out for now because the GPU test are not working inside docker
export CUDA_ARCH_VERSION=${{ matrix.cuda_arch_version }}
export CU_VERSION="cu${CUDA_ARCH_VERSION:0:2}${CUDA_ARCH_VERSION:3:1}"
if [[ "${{ github.ref }}" =~ release/* ]]; then
export RELEASE=1
export TORCH_VERSION=stable
else
export RELEASE=0
export TORCH_VERSION=nightly
fi
export TD_GET_DEFAULTS_TO_NONE=1
echo "PYTHON_VERSION: $PYTHON_VERSION"
echo "CU_VERSION: $CU_VERSION"
## setup_env.sh
bash .github/unittest/linux_optdeps/scripts/run_all.sh
tests-stable-gpu:
strategy:
matrix:
python_version: ["3.10"] # "3.9", "3.10", "3.11"
cuda_arch_version: ["11.8"] # "11.6", "11.7"
fail-fast: false
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.g5.4xlarge.nvidia.gpu
repository: pytorch/rl
docker-image: "nvidia/cuda:12.1.0-devel-ubuntu22.04"
gpu-arch-type: cuda
gpu-arch-version: ${{ matrix.cuda_arch_version }}
timeout: 90
script: |
# Set env vars from matrix
export PYTHON_VERSION=${{ matrix.python_version }}
# Commenting these out for now because the GPU test are not working inside docker
export CUDA_ARCH_VERSION=${{ matrix.cuda_arch_version }}
export CU_VERSION="cu${CUDA_ARCH_VERSION:0:2}${CUDA_ARCH_VERSION:3:1}"
if [[ "${{ github.ref }}" =~ release/* ]]; then
export RELEASE=1
export TORCH_VERSION=stable
else
export RELEASE=0
export TORCH_VERSION=nightly
fi
# Remove the following line when the GPU tests are working inside docker, and uncomment the above lines
#export CU_VERSION="cpu"
echo "PYTHON_VERSION: $PYTHON_VERSION"
echo "CU_VERSION: $CU_VERSION"
export TD_GET_DEFAULTS_TO_NONE=1
## setup_env.sh
bash .github/unittest/linux/scripts/run_all.sh