{{ message }}
Repository navigation
464 lines (434 loc) · 15.7 KB
/
Copy pathnightly_tests.yml
File metadata and controls
464 lines (434 loc) · 15.7 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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
name: Nightly and release tests on main/release branch
on:
workflow_dispatch:
schedule:
- cron: "0 0 * * *" # every day at midnight
env:
DIFFUSERS_IS_CI: yes
HF_HUB_ENABLE_HF_TRANSFER: 1
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
PYTEST_TIMEOUT: 600
RUN_SLOW: yes
RUN_NIGHTLY: yes
PIPELINE_USAGE_CUTOFF: 5000
SLACK_API_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
jobs:
setup_torch_cuda_pipeline_matrix:
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: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
pip install -e .[test]
pip install huggingface_hub
- name: Fetch Pipeline Matrix
id: fetch_pipeline_matrix
run: |
matrix=$(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@v4
with:
name: test-pipelines.json
path: reports
run_nightly_tests_for_torch_pipelines:
name: Nightly Torch Pipelines CUDA Tests
needs: setup_torch_cuda_pipeline_matrix
strategy:
fail-fast: false
max-parallel: 8
matrix:
module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
runs-on:
group: aws-g4dn-2xlarge
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host --gpus 0
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: nvidia-smi
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
python -m uv pip install pytest-reportlog
- name: Environment
run: |
python utils/print_env.py
- name: Pipeline CUDA Test
env:
HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
# https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
CUBLAS_WORKSPACE_CONFIG: :16:8
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v -k "not Flax and not Onnx" \
--make-reports=tests_pipeline_${{ matrix.module }}_cuda \
--report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
tests/pipelines/${{ matrix.module }}
- 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: ${{ always() }}
uses: actions/upload-artifact@v4
with:
name: pipeline_${{ matrix.module }}_test_reports
path: reports
- name: Generate Report and Notify Channel
if: always()
run: |
pip install slack_sdk tabulate
python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
run_nightly_tests_for_other_torch_modules:
name: Nightly Torch CUDA Tests
runs-on:
group: aws-g4dn-2xlarge
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host --gpus 0
defaults:
run:
shell: bash
strategy:
fail-fast: false
max-parallel: 2
matrix:
module: [models, schedulers, lora, others, single_file, examples]
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install peft@git+https://github.com/huggingface/peft.git
pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
python -m uv pip install pytest-reportlog
- name: Environment
run: python utils/print_env.py
- name: Run nightly PyTorch CUDA tests for non-pipeline modules
if: ${{ matrix.module != 'examples'}}
env:
HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
# https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
CUBLAS_WORKSPACE_CONFIG: :16:8
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v -k "not Flax and not Onnx" \
--make-reports=tests_torch_${{ matrix.module }}_cuda \
--report-log=tests_torch_${{ matrix.module }}_cuda.log \
tests/${{ matrix.module }}
- name: Run nightly example tests with Torch
if: ${{ matrix.module == 'examples' }}
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: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v --make-reports=examples_torch_cuda \
--report-log=examples_torch_cuda.log \
examples/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_torch_${{ matrix.module }}_cuda_stats.txt
cat reports/tests_torch_${{ matrix.module }}_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v4
with:
name: torch_${{ matrix.module }}_cuda_test_reports
path: reports
- name: Generate Report and Notify Channel
if: always()
run: |
pip install slack_sdk tabulate
python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
run_big_gpu_torch_tests:
name: Torch tests on big GPU
strategy:
fail-fast: false
max-parallel: 2
runs-on:
group: aws-g6e-xlarge-plus
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host --gpus 0
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: nvidia-smi
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install peft@git+https://github.com/huggingface/peft.git
pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
python -m uv pip install pytest-reportlog
- name: Environment
run: |
python utils/print_env.py
- name: Selected Torch CUDA Test on big GPU
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
BIG_GPU_MEMORY: 40
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-m "big_gpu_with_torch_cuda" \
--make-reports=tests_big_gpu_torch_cuda \
--report-log=tests_big_gpu_torch_cuda.log \
tests/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_big_gpu_torch_cuda_stats.txt
cat reports/tests_big_gpu_torch_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v4
with:
name: torch_cuda_big_gpu_test_reports
path: reports
- name: Generate Report and Notify Channel
if: always()
run: |
pip install slack_sdk tabulate
python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
run_flax_tpu_tests:
name: Nightly Flax TPU Tests
runs-on: docker-tpu
if: github.event_name == 'schedule'
container:
image: diffusers/diffusers-flax-tpu
options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
defaults:
run:
shell: bash
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
python -m uv pip install pytest-reportlog
- name: Environment
run: python utils/print_env.py
- name: Run nightly Flax TPU tests
env:
HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
run: |
python -m pytest -n 0 \
-s -v -k "Flax" \
--make-reports=tests_flax_tpu \
--report-log=tests_flax_tpu.log \
tests/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_flax_tpu_stats.txt
cat reports/tests_flax_tpu_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v4
with:
name: flax_tpu_test_reports
path: reports
- name: Generate Report and Notify Channel
if: always()
run: |
pip install slack_sdk tabulate
python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
run_nightly_onnx_tests:
name: Nightly ONNXRuntime CUDA tests on Ubuntu
runs-on:
group: aws-g4dn-2xlarge
container:
image: diffusers/diffusers-onnxruntime-cuda
options: --gpus 0 --shm-size "16gb" --ipc host
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: nvidia-smi
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
python -m uv pip install pytest-reportlog
- name: Environment
run: python utils/print_env.py
- name: Run Nightly ONNXRuntime CUDA tests
env:
HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v -k "Onnx" \
--make-reports=tests_onnx_cuda \
--report-log=tests_onnx_cuda.log \
tests/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_onnx_cuda_stats.txt
cat reports/tests_onnx_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v4
with:
name: tests_onnx_cuda_reports
path: reports
- name: Generate Report and Notify Channel
if: always()
run: |
pip install slack_sdk tabulate
python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
# M1 runner currently not well supported
# TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
# run_nightly_tests_apple_m1:
# name: Nightly PyTorch MPS tests on MacOS
# runs-on: [ self-hosted, apple-m1 ]
# if: github.event_name == 'schedule'
#
# steps:
# - name: Checkout diffusers
# uses: actions/checkout@v3
# with:
# fetch-depth: 2
#
# - name: Clean checkout
# shell: arch -arch arm64 bash {0}
# run: |
# git clean -fxd
# - name: Setup miniconda
# uses: ./.github/actions/setup-miniconda
# with:
# python-version: 3.9
#
# - name: Install dependencies
# shell: arch -arch arm64 bash {0}
# run: |
# ${CONDA_RUN} python -m pip install --upgrade pip uv
# ${CONDA_RUN} python -m uv pip install -e [quality,test]
# ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
# ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
# ${CONDA_RUN} python -m uv pip install pytest-reportlog
# - name: Environment
# shell: arch -arch arm64 bash {0}
# run: |
# ${CONDA_RUN} python utils/print_env.py
# - name: Run nightly PyTorch tests on M1 (MPS)
# shell: arch -arch arm64 bash {0}
# env:
# HF_HOME: /System/Volumes/Data/mnt/cache
# HF_TOKEN: ${{ secrets.HF_TOKEN }}
# run: |
# ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
# --report-log=tests_torch_mps.log \
# tests/
# - name: Failure short reports
# if: ${{ failure() }}
# run: cat reports/tests_torch_mps_failures_short.txt
#
# - name: Test suite reports artifacts
# if: ${{ always() }}
# uses: actions/upload-artifact@v4
# with:
# name: torch_mps_test_reports
# path: reports
#
# - name: Generate Report and Notify Channel
# if: always()
# run: |
# pip install slack_sdk tabulate
# python utils/log_reports.py >> $GITHUB_STEP_SUMMARY run_nightly_tests_apple_m1:
# name: Nightly PyTorch MPS tests on MacOS
# runs-on: [ self-hosted, apple-m1 ]
# if: github.event_name == 'schedule'
#
# steps:
# - name: Checkout diffusers
# uses: actions/checkout@v3
# with:
# fetch-depth: 2
#
# - name: Clean checkout
# shell: arch -arch arm64 bash {0}
# run: |
# git clean -fxd
# - name: Setup miniconda
# uses: ./.github/actions/setup-miniconda
# with:
# python-version: 3.9
#
# - name: Install dependencies
# shell: arch -arch arm64 bash {0}
# run: |
# ${CONDA_RUN} python -m pip install --upgrade pip uv
# ${CONDA_RUN} python -m uv pip install -e [quality,test]
# ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
# ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
# ${CONDA_RUN} python -m uv pip install pytest-reportlog
# - name: Environment
# shell: arch -arch arm64 bash {0}
# run: |
# ${CONDA_RUN} python utils/print_env.py
# - name: Run nightly PyTorch tests on M1 (MPS)
# shell: arch -arch arm64 bash {0}
# env:
# HF_HOME: /System/Volumes/Data/mnt/cache
# HF_TOKEN: ${{ secrets.HF_TOKEN }}
# run: |
# ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
# --report-log=tests_torch_mps.log \
# tests/
# - name: Failure short reports
# if: ${{ failure() }}
# run: cat reports/tests_torch_mps_failures_short.txt
#
# - name: Test suite reports artifacts
# if: ${{ always() }}
# uses: actions/upload-artifact@v4
# with:
# name: torch_mps_test_reports
# path: reports
#
# - name: Generate Report and Notify Channel
# if: always()
# run: |
# pip install slack_sdk tabulate
# python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
You can’t perform that action at this time.