forked from huggingface/diffusers
-
Notifications
You must be signed in to change notification settings - Fork 0
294 lines (267 loc) 路 9.9 KB
/
Copy pathpr_tests_gpu.yml
File metadata and controls
294 lines (267 loc) 路 9.9 KB
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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
name: Fast GPU Tests on PR
permissions:
contents: read
on:
pull_request:
branches: main
paths:
- "src/diffusers/models/modeling_utils.py"
- "src/diffusers/models/model_loading_utils.py"
- "src/diffusers/pipelines/pipeline_utils.py"
- "src/diffusers/pipeline_loading_utils.py"
- "src/diffusers/loaders/lora_base.py"
- "src/diffusers/loaders/lora_pipeline.py"
- "src/diffusers/loaders/peft.py"
- "tests/pipelines/test_pipelines_common.py"
- "tests/models/test_modeling_common.py"
- "examples/**/*.py"
workflow_dispatch:
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
env:
DIFFUSERS_IS_CI: yes
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
HF_XET_HIGH_PERFORMANCE: 1
PYTEST_TIMEOUT: 600
PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
jobs:
check_code_quality:
runs-on: ubuntu-22.04
steps:
- uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: "3.10"
- name: Install dependencies
run: |
pip install --upgrade pip
pip install .[quality]
- name: Check quality
run: make quality
- name: Check if failure
if: ${{ failure() }}
run: |
echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
check_repository_consistency:
needs: check_code_quality
runs-on: ubuntu-22.04
steps:
- uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: "3.10"
- name: Install dependencies
run: |
pip install --upgrade pip
pip install .[quality]
- name: Check repo consistency
run: |
python utils/check_copies.py
python utils/check_dummies.py
python utils/check_support_list.py
make deps_table_check_updated
- name: Check if failure
if: ${{ failure() }}
run: |
echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
setup_torch_cuda_pipeline_matrix:
needs: [check_code_quality, check_repository_consistency]
name: Setup Torch Pipelines CUDA Slow Tests Matrix
runs-on:
group: aws-general-8-plus
container:
image: diffusers/diffusers-pytorch-cpu
outputs:
pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
steps:
- name: Checkout diffusers
uses: actions/checkout@v6
with:
fetch-depth: 2
- name: Install dependencies
run: |
uv pip install -e ".[quality]"
- name: Environment
run: |
python utils/print_env.py
- name: Fetch Pipeline Matrix
id: fetch_pipeline_matrix
run: |
matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
echo $matrix
echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
- name: Pipeline Tests Artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v6
with:
name: test-pipelines.json
path: reports
torch_pipelines_cuda_tests:
name: Torch Pipelines CUDA Tests
needs: setup_torch_cuda_pipeline_matrix
strategy:
fail-fast: false
max-parallel: 8
matrix:
module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
runs-on:
group: aws-g4dn-2xlarge
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host --gpus all
steps:
- name: Checkout diffusers
uses: actions/checkout@v6
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Install dependencies
run: |
uv pip install -e ".[quality]"
uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
- name: Environment
run: |
python utils/print_env.py
- name: Extract tests
id: extract_tests
run: |
pattern=$(python utils/extract_tests_from_mixin.py --type pipeline)
echo "$pattern" > /tmp/test_pattern.txt
echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
- name: PyTorch CUDA checkpoint tests on Ubuntu
env:
HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
# https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
CUBLAS_WORKSPACE_CONFIG: :16:8
run: |
if [ "${{ matrix.module }}" = "ip_adapters" ]; then
pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-k "not Flax and not Onnx" \
--make-reports=tests_pipeline_${{ matrix.module }}_cuda \
tests/pipelines/${{ matrix.module }}
else
pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-k "not Flax and not Onnx and $pattern" \
--make-reports=tests_pipeline_${{ matrix.module }}_cuda \
tests/pipelines/${{ matrix.module }}
fi
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v6
with:
name: pipeline_${{ matrix.module }}_test_reports
path: reports
torch_cuda_tests:
name: Torch CUDA Tests
needs: [check_code_quality, check_repository_consistency]
runs-on:
group: aws-g4dn-2xlarge
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host --gpus all
defaults:
run:
shell: bash
strategy:
fail-fast: false
max-parallel: 4
matrix:
module: [models, schedulers, lora, others]
steps:
- name: Checkout diffusers
uses: actions/checkout@v6
with:
fetch-depth: 2
- name: Install dependencies
run: |
uv pip install -e ".[quality]"
uv pip install peft@git+https://github.com/huggingface/peft.git
uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
- name: Environment
run: |
python utils/print_env.py
- name: Extract tests
id: extract_tests
run: |
pattern=$(python utils/extract_tests_from_mixin.py --type ${{ matrix.module }})
echo "$pattern" > /tmp/test_pattern.txt
echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
- name: Run PyTorch CUDA tests
env:
HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
# https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
CUBLAS_WORKSPACE_CONFIG: :16:8
run: |
pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
if [ -z "$pattern" ]; then
pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
--make-reports=tests_torch_cuda_${{ matrix.module }}
else
pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
--make-reports=tests_torch_cuda_${{ matrix.module }}
fi
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_torch_cuda_${{ matrix.module }}_stats.txt
cat reports/tests_torch_cuda_${{ matrix.module }}_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v6
with:
name: torch_cuda_test_reports_${{ matrix.module }}
path: reports
run_examples_tests:
name: Examples PyTorch CUDA tests on Ubuntu
needs: [check_code_quality, check_repository_consistency]
runs-on:
group: aws-g4dn-2xlarge
container:
image: diffusers/diffusers-pytorch-cuda
options: --gpus all --shm-size "16gb" --ipc host
steps:
- name: Checkout diffusers
uses: actions/checkout@v6
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Install dependencies
run: |
uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
uv pip install -e ".[quality,training]"
- name: Environment
run: |
python utils/print_env.py
- name: Run example tests on GPU
env:
HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
run: |
uv pip install ".[training]"
pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/examples_torch_cuda_stats.txt
cat reports/examples_torch_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v6
with:
name: examples_test_reports
path: reports