-
Notifications
You must be signed in to change notification settings - Fork 445
661 lines (643 loc) · 32.1 KB
/
daily_ete_test.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
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
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
name: daily_ete_test
on:
workflow_dispatch:
inputs:
repo_org:
required: false
description: 'Tested repository organization name. Default is InternLM'
type: string
default: 'InternLM/lmdeploy'
repo_ref:
required: false
description: 'Set branch or tag or commit id. Default is "main"'
type: string
default: 'main'
backend:
required: true
description: 'Set backend testcase filter: turbomind or pytorch or turbomind, pytorch. Default is "["turbomind", "pytorch"]"'
type: string
default: "['turbomind', 'pytorch', 'turbomind_vl']"
model:
required: true
description: 'Set testcase module filter: chat, restful, pipeline, quantization. Default contains all models'
type: string
default: "['pipeline','restful','chat']"
offline_mode:
required: true
description: 'Whether start a offline mode, if true, you should prepare code and whl package by yourself'
type: boolean
default: false
regression_func:
required: true
description: 'regression functions'
type: string
default: "['quant', 'tools','restful','pipeline','benchmark','evaluation']"
schedule:
- cron: '00 16 * * 0-4'
env:
HOST_PIP_CACHE_DIR: /nvme/github-actions/pip-cache
HOST_LOCALTIME: /usr/share/zoneinfo/Asia/Shanghai
OUTPUT_FOLDER: cuda11.8_dist_${{ github.run_id }}
ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
REPORT_DIR: /nvme/qa_test_models/test-reports/${{ github.run_id }}
COV_PARAM: --cov /opt/py3/lib/python3.10/site-packages/lmdeploy
FAIL_CONFIG: ${{ github.event_name == 'schedule' && github.run_attempt != 1 && '--lf --lfnf none' || '--lf'}}
TEST_CODE_PATH: /nvme/qa_test_models/test_pkg/lmdeploy
OFFLINE_CODE_PATH: /nvme/qa_test_models/offline_pkg/lmdeploy
OFFLINE_REQUIREMENTS: /nvme/qa_test_models/offline_pkg/requirements.txt
DEEPSEEK_VL: /nvme/qa_test_models/offline_pkg/DeepSeek-VL
jobs:
linux-build:
if: ${{!cancelled() && (github.event_name == 'schedule' || !inputs.offline_mode)}}
strategy:
matrix:
pyver: [py310]
runs-on: ubuntu-latest
env:
PYTHON_VERSION: ${{ matrix.pyver }}
PLAT_NAME: manylinux2014_x86_64
DOCKER_TAG: cuda11.8
steps:
- name: Checkout repository
uses: actions/checkout@v3
with:
repository: ${{ github.event.inputs.repo_org || 'InternLM/lmdeploy' }}
ref: ${{github.event.inputs.repo_ref || 'main'}}
- name: Build
run: |
echo ${PYTHON_VERSION}
echo ${PLAT_NAME}
echo ${DOCKER_TAG}
echo ${OUTPUT_FOLDER}
echo ${GITHUB_RUN_ID}
# remove -it
sed -i 's/docker run --rm -it/docker run --rm/g' builder/manywheel/build_wheel.sh
bash builder/manywheel/build_wheel.sh ${PYTHON_VERSION} ${PLAT_NAME} ${DOCKER_TAG} ${OUTPUT_FOLDER}
- name: Upload Artifacts
uses: actions/upload-artifact@v4
with:
if-no-files-found: error
path: builder/manywheel/${{ env.OUTPUT_FOLDER }}
retention-days: 1
name: my-artifact-${{ github.run_id }}-${{ matrix.pyver }}
download_pkgs:
needs: linux-build
if: ${{!cancelled()}}
runs-on: [self-hosted, linux-a100]
timeout-minutes: 50
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/qa_test_models:/nvme/qa_test_models
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Clone repository
uses: actions/checkout@v2
if: ${{github.event_name == 'schedule' || !inputs.offline_mode}}
with:
repository: ${{ github.event.inputs.repo_org || 'InternLM/lmdeploy' }}
ref: ${{github.event.inputs.repo_ref || 'main'}}
- name: Copy repository
if: ${{github.event_name == 'schedule' || !inputs.offline_mode}}
run: rm -rf ${{env.TEST_CODE_PATH}} && mkdir ${{env.TEST_CODE_PATH}} && cp -r . ${{env.TEST_CODE_PATH}}
- name: Copy repository - offline
if: ${{inputs.offline_mode}}
run: rm -rf ${{env.TEST_CODE_PATH}} && mkdir ${{env.TEST_CODE_PATH}} && cp -r ${{env.OFFLINE_CODE_PATH}}/. ${{env.TEST_CODE_PATH}}
- name: Download Artifacts
if: ${{github.event_name == 'schedule' || !inputs.offline_mode}}
uses: actions/download-artifact@v4
with:
name: my-artifact-${{ github.run_id }}-py310
- name: Copy Artifacts
if: ${{github.event_name == 'schedule' || !inputs.offline_mode}}
run: rm ${{env.TEST_CODE_PATH}}/lmdeploy-*.whl -f && cp lmdeploy-*.whl ${{env.TEST_CODE_PATH}}
- name: Copy Artifacts - offline
if: ${{inputs.offline_mode}}
run: rm ${{env.TEST_CODE_PATH}}/lmdeploy-*.whl -f && cp ${{env.OFFLINE_CODE_PATH}}/lmdeploy-*.whl ${{env.TEST_CODE_PATH}}
test_quantization:
needs: download_pkgs
if: ${{!cancelled() && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'quant') )}}
runs-on: [self-hosted, linux-a100]
timeout-minutes: 120
env:
PYTHONPATH: /nvme/qa_test_models/offline_pkg/LLaVA
MODELSCOPE_CACHE: /root/modelscope_hub
MODELSCOPE_MODULES_CACHE: /root/modelscope_modules
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/github-actions/pip-cache:/root/.cache/pip
- /nvme/github-actions/packages:/root/packages
- /nvme/github-actions/modelscope_hub:/root/modelscope_hub
- /nvme/github-actions/modelscope_modules:/root/modelscope_modules
- /nvme/github-actions/resources/lora:/root/lora
- /nvme/qa_test_models:/nvme/qa_test_models
- /mnt/shared:/mnt/shared
- /nvme/qa_test_models/lmdeploy/autotest:/local_case
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Copy repository and Artifacts
run: cp -r ${{env.TEST_CODE_PATH}}/. .
- name: Install lmdeploy - dependency
run: |
# manually install flash attn
# the install packeage from. https://github.com/Dao-AILab/flash-attention/releases
python3 -m pip install /root/packages/flash_attn-2.6.3+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
python3 -m pip install -e /root/packages/AutoAWQ_kernels
python3 -m pip install /root/packages/autoawq-0.2.6-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install /root/packages/xformers-0.0.27+cu118-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
- name: Install lmdeploy
run: |
python3 -m pip install lmdeploy-*.whl --no-deps
python3 -m pip install -r requirements/test.txt
pip install ${{env.DEEPSEEK_VL}} --no-deps
- name: Check env
run: |
pip install transformers==4.44.2
pip uninstall -y nvidia-nccl-cu11
python3 -m pip list
lmdeploy check_env
cp -r /root/lora .
rm -rf allure-results
# remove tmp log in testcase
rm -rf /nvme/qa_test_models/autotest_model/log/*
mkdir ${{env.REPORT_DIR}}/.pytest_cache -p
ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
- name: Test lmdeploy - quantization w4a16
continue-on-error: true
if: github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.backend), 'turbomind')
run: |
pytest autotest/tools/quantization/test_quantization_awq.py -m 'not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} --clean-alluredir ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Test lmdeploy - quantization w8a8
continue-on-error: true
if: github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.backend), 'pytorch')
run: |
pytest autotest/tools/quantization/test_quantization_w8a8.py -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Test lmdeploy - convert
continue-on-error: true
if: github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.backend), 'turbomind')
run: |
pytest autotest/tools/convert -m 'not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Clear workfile
if: always()
run: |
chmod -R 777 $REPORT_DIR
export workdir=$(pwd)
cd ..
rm -rf $workdir
mkdir $workdir
chmod -R 777 $workdir
test_tools:
needs: test_quantization
if: ${{!cancelled() && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'tools'))}}
runs-on: [self-hosted, linux-a100]
timeout-minutes: 120
strategy:
fail-fast: false
matrix:
backend: ${{ fromJSON(inputs.backend) || fromJSON('["turbomind", "pytorch", "turbomind_vl"]')}}
model: ${{ fromJSON(inputs.model) || fromJSON('["pipeline","restful","chat"]')}}
include:
- backend: turbomind
- model: lcoal_case
env:
PYTHONPATH: /nvme/qa_test_models/offline_pkg/LLaVA
MODELSCOPE_CACHE: /root/modelscope_hub
MODELSCOPE_MODULES_CACHE: /root/modelscope_modules
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/github-actions/pip-cache:/root/.cache/pip
- /nvme/github-actions/packages:/root/packages
- /nvme/github-actions/modelscope_hub:/root/modelscope_hub
- /nvme/github-actions/modelscope_modules:/root/modelscope_modules
- /nvme/github-actions/resources/lora:/root/lora
- /nvme/qa_test_models:/nvme/qa_test_models
- /mnt/shared:/mnt/shared
- /nvme/qa_test_models/lmdeploy/autotest:/local_case
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Copy repository and Artifacts
run: cp -r ${{env.TEST_CODE_PATH}}/. .
- name: Install lmdeploy - dependency
run: |
# manually install flash attn
# the install packeage from. https://github.com/Dao-AILab/flash-attention/releases
python3 -m pip install /root/packages/flash_attn-2.6.3+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
python3 -m pip install -e /root/packages/AutoAWQ_kernels
python3 -m pip install /root/packages/autoawq-0.2.6-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install /root/packages/xformers-0.0.27+cu118-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
- name: Install lmdeploy
run: |
python3 -m pip install lmdeploy-*.whl --no-deps
python3 -m pip install -r requirements/test.txt
pip install ${{env.DEEPSEEK_VL}} --no-deps
- name: Check env
run: |
pip uninstall -y nvidia-nccl-cu11
python3 -m pip list
lmdeploy check_env
cp -r /root/lora .
rm -rf allure-results
# remove tmp log in testcase
rm -rf /nvme/qa_test_models/autotest_model/log/*
mkdir ${{env.REPORT_DIR}}/.pytest_cache -p
ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
- name: Test lmdeploy - chat workspace
continue-on-error: true
if: matrix.backend == 'turbomind' && matrix.model == 'chat'
run: |
pytest autotest/tools/chat/test_command_chat_workspace.py -m 'gpu_num_1 and not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/tools/chat/test_command_chat_workspace.py -m 'gpu_num_2 and not pr_test' -n 4 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Test lmdeploy - chat
continue-on-error: true
if: (matrix.backend == 'pytorch' || matrix.backend == 'turbomind') && matrix.model == 'chat'
run: |
pytest autotest/tools/chat/test_command_chat_hf_${{matrix.backend}}.py -m 'gpu_num_1 and not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/tools/chat/test_command_chat_hf_${{matrix.backend}}.py -m 'gpu_num_2 and not pr_test' -n 4 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Test lmdeploy - pipeline
continue-on-error: true
if: matrix.model == 'pipeline'
run: |
pytest autotest/tools/pipeline/test_pipeline_chat_${{matrix.backend}}.py -m 'gpu_num_1 and not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/tools/pipeline/test_pipeline_chat_${{matrix.backend}}.py -m 'gpu_num_2 and not pr_test' -n 4 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Test lmdeploy - restful
continue-on-error: true
if: matrix.model == 'restful'
run: |
pytest autotest/tools/restful/test_restful_chat_hf_${{matrix.backend}}.py -m 'gpu_num_1 and not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/tools/restful/test_restful_chat_hf_${{matrix.backend}}.py -m 'gpu_num_2 and not pr_test' -n 4 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Test lmdeploy - restful workspace
continue-on-error: true
if: matrix.backend == 'turbomind' && matrix.model == 'restful'
run: |
pytest autotest/tools/restful/test_restful_chat_workspace.py -m 'gpu_num_1 and not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/tools/restful/test_restful_chat_workspace.py -m 'gpu_num_2 and not pr_test' -n 4 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Test lmdeploy - local testcase
if: matrix.backend == 'turbomind' && matrix.model == 'local_case'
run: |
pytest /local_case/issue_regression --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}}|| true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Clear workfile
if: always()
run: |
chmod -R 777 $REPORT_DIR
export workdir=$(pwd)
cd ..
rm -rf $workdir
mkdir $workdir
chmod -R 777 $workdir
test_restful:
if: ${{!cancelled() && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'restful'))}}
runs-on: [self-hosted, linux-a100]
needs: test_quantization
strategy:
fail-fast: false
matrix:
backend: ['turbomind', 'pytorch']
timeout-minutes: 60
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/github-actions/pip-cache:/root/.cache/pip
- /nvme/github-actions/packages:/root/packages
- /nvme/qa_test_models:/nvme/qa_test_models
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Copy repository and Artifacts
run: cp -r ${{env.TEST_CODE_PATH}}/. .
- name: Install lmdeploy - dependency
run: |
# manually install flash attn
# the install packeage from. https://github.com/Dao-AILab/flash-attention/releases
python3 -m pip install /root/packages/flash_attn-2.6.3+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
python3 -m pip install -e /root/packages/AutoAWQ_kernels
python3 -m pip install /root/packages/autoawq-0.2.6-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install /root/packages/xformers-0.0.27+cu118-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
- name: Install lmdeploy
run: |
python3 -m pip install lmdeploy-*.whl --no-deps
python3 -m pip install -r requirements/test.txt
pip install ${{env.DEEPSEEK_VL}} --no-deps
- name: Check env
run: |
pip uninstall -y nvidia-nccl-cu11
python3 -m pip list
lmdeploy check_env
cp -r /root/lora .
rm -rf allure-results
# remove tmp log in testcase
rm -rf /nvme/qa_test_models/autotest_model/log/*
mkdir ${{env.REPORT_DIR}}/.pytest_cache -p
ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
- name: Start restful api turbomind
if: matrix.backend == 'turbomind'
run: |
CUDA_VISIBLE_DEVICES=6,7 lmdeploy serve api_server /nvme/qa_test_models/internlm/internlm2_5-20b-chat --tp 2 > restful.log 2>&1 &
echo "restful_pid=$!" >> "$GITHUB_ENV"
sleep 120s
- name: Start restful api pytorch
if: matrix.backend == 'pytorch'
run: |
CUDA_VISIBLE_DEVICES=6,7 lmdeploy serve api_server /nvme/qa_test_models/internlm/internlm2_5-20b-chat --tp 2 --backend pytorch > restful.log 2>&1 &
echo "restful_pid=$!" >> "$GITHUB_ENV"
sleep 180s
- name: Test lmdeploy - restful api
timeout-minutes: 75
run: |
pytest autotest/interface/restful/test_restful_chat_func.py -n 20 -m 'not not_${{matrix.backend}}' --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Kill api server
if: always()
run: |
kill -15 "$restful_pid"
- name: Start restful api turbomind - base
if: matrix.backend == 'turbomind'
run: |
CUDA_VISIBLE_DEVICES=6,7 lmdeploy serve api_server /nvme/qa_test_models/internlm/internlm2_5-20b --tp 2 > restful.log 2>&1 &
echo "restful_pid=$!" >> "$GITHUB_ENV"
sleep 120s
- name: Start restful api pytorch - base
if: matrix.backend == 'pytorch'
run: |
CUDA_VISIBLE_DEVICES=6,7 lmdeploy serve api_server /nvme/qa_test_models/internlm/internlm2_5-20b --tp 2 --backend pytorch > restful.log 2>&1 &
echo "restful_pid=$!" >> "$GITHUB_ENV"
sleep 180s
- name: Test lmdeploy - restful api - base
timeout-minutes: 40
run: |
pytest autotest/interface/restful/test_restful_completions_v1.py -n 20 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Kill api server
if: always()
run: |
kill -15 "$restful_pid"
- name: Clear workfile
if: always()
run: |
chmod -R 777 $REPORT_DIR
export workdir=$(pwd)
cd ..
rm -rf $workdir
mkdir $workdir
chmod -R 777 $workdir
test_pipeline:
if: ${{!cancelled() && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'pipeline'))}}
runs-on: [self-hosted, linux-a100]
needs: test_quantization
timeout-minutes: 120
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/github-actions/pip-cache:/root/.cache/pip
- /nvme/github-actions/packages:/root/packages
- /nvme/qa_test_models:/nvme/qa_test_models
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Copy repository and Artifacts
run: cp -r ${{env.TEST_CODE_PATH}}/. .
- name: Install lmdeploy - dependency
run: |
# manually install flash attn
# the install packeage from. https://github.com/Dao-AILab/flash-attention/releases
python3 -m pip install /root/packages/flash_attn-2.6.3+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
python3 -m pip install -e /root/packages/AutoAWQ_kernels
python3 -m pip install /root/packages/autoawq-0.2.6-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install /root/packages/xformers-0.0.27+cu118-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
- name: Install lmdeploy
run: |
python3 -m pip install lmdeploy-*.whl --no-deps
python3 -m pip install -r requirements/test.txt
pip install ${{env.DEEPSEEK_VL}} --no-deps
- name: Check env
run: |
pip uninstall -y nvidia-nccl-cu11
python3 -m pip list
lmdeploy check_env
cp -r /root/lora .
rm -rf allure-results
# remove tmp log in testcase
rm -rf /nvme/qa_test_models/autotest_model/log/*
mkdir ${{env.REPORT_DIR}}/.pytest_cache -p
ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
- name: Test lmdeploy - interface pipeline case
run: |
pytest autotest/interface/pipeline/test_pipeline_func.py -m 'not pr_test' -n 4 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/interface/pipeline/test_pipeline_longtext_func.py -m 'gpu_num_1 and not pr_test' -n 8 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/interface/pipeline/test_pipeline_longtext_func.py -m 'gpu_num_2 and not pr_test' -n 4 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S') || true
pytest autotest/interface/pipeline/test_pipeline_longtext_func.py -m 'gpu_num_4 and not pr_test' -n 2 --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Clear workfile
if: always()
run: |
chmod -R 777 $REPORT_DIR
export workdir=$(pwd)
cd ..
rm -rf $workdir
mkdir $workdir
chmod -R 777 $workdir
test_benchmark:
if: ${{!cancelled() && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'benchmark'))}}
runs-on: [self-hosted, linux-a100]
needs: test_quantization
timeout-minutes: 120
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/github-actions/pip-cache:/root/.cache/pip
- /nvme/github-actions/packages:/root/packages
- /nvme/qa_test_models:/nvme/qa_test_models
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Copy repository and Artifacts
run: cp -r ${{env.TEST_CODE_PATH}}/. .
- name: Install lmdeploy - dependency
run: |
# manually install flash attn
# the install packeage from. https://github.com/Dao-AILab/flash-attention/releases
python3 -m pip install /root/packages/flash_attn-2.6.3+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
python3 -m pip install -e /root/packages/AutoAWQ_kernels
python3 -m pip install /root/packages/autoawq-0.2.6-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install /root/packages/xformers-0.0.27+cu118-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
- name: Install lmdeploy
run: |
python3 -m pip install lmdeploy-*.whl --no-deps
python3 -m pip install -r requirements/test.txt
pip install ${{env.DEEPSEEK_VL}} --no-deps
- name: Check env
run: |
pip uninstall -y nvidia-nccl-cu11
python3 -m pip list
lmdeploy check_env
cp -r /root/lora .
rm -rf allure-results
# remove tmp log in testcase
rm -rf /nvme/qa_test_models/autotest_model/log/*
mkdir ${{env.REPORT_DIR}}/.pytest_cache -p
ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
- name: Test benchmark script
run: |
pytest autotest/benchmark -n 4 --run_id ${{ github.run_id }} -m function ${{env.FAIL_CONFIG}} --alluredir=${{env.REPORT_DIR}} ${{env.COV_PARAM}} || true
mv .coverage ${{env.REPORT_DIR}}/.coverage.$(date +'%Y%m%d%H%M%S')
- name: Clear workfile
if: always()
run: |
chmod -R 777 $REPORT_DIR
chmod -R 777 /nvme/qa_test_models/benchmark-reports/${{ github.run_id }}
export workdir=$(pwd)
cd ..
rm -rf $workdir
mkdir $workdir
chmod -R 777 $workdir
test_evaluation:
if: ${{!cancelled() && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'evaluation'))}}
runs-on: [self-hosted, linux-a100]
needs: test_quantization
timeout-minutes: 120 # 5hours
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/github-actions/pip-cache:/root/.cache/pip
- /nvme/github-actions/packages:/root/packages
- /nvme/github-actions/resources:/root/resources
- /nvme/github-actions/opencompass-data:/root/opencompass-data
- /nvme/qa_test_models/evaluation-reports:/root/evaluation-reports
- /nvme/qa_test_models:/root/models
- /nvme/qa_test_models/offline_pkg:/nvme/qa_test_models/offline_pkg
- /mnt/shared:/mnt/shared
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Copy repository and Artifacts
run: cp -r ${{env.TEST_CODE_PATH}}/. .
- name: Install lmdeploy - dependency
run: |
# manually install flash attn
# the install packeage from. https://github.com/Dao-AILab/flash-attention/releases
python3 -m pip install /root/packages/flash_attn-2.6.3+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
python3 -m pip install -e /root/packages/AutoAWQ_kernels
python3 -m pip install /root/packages/autoawq-0.2.6-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install /root/packages/xformers-0.0.27+cu118-cp310-cp310-manylinux2014_x86_64.whl --no-deps
python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
- name: Install lmdeploy
run: |
python3 -m pip install lmdeploy-*.whl --no-deps
python3 -m pip install -r requirements/test.txt
pip install ${{env.DEEPSEEK_VL}} --no-deps
- name: Check env
run: |
pip uninstall -y nvidia-nccl-cu11
python3 -m pip list
lmdeploy check_env
cp -r /root/lora .
rm -rf allure-results
# remove tmp log in testcase
rm -rf /nvme/qa_test_models/autotest_model/log/*
mkdir ${{env.REPORT_DIR}}/.pytest_cache -p
ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
- name: Setup paths for evaluation
run: |
ln -s /root/opencompass-data ./data
python3 .github/scripts/action_tools.py create_model_links /root/models .
- name: Evaluate models
run: |
export LMDEPLOY_DIR=$(pwd)
python3 .github/scripts/action_tools.py evaluate "[turbomind_internlm2_5_7b_chat, turbomind_internlm2_5_7b_chat_4bits, turbomind_internlm2_5_7b_chat_kvint4, pt_internlm2_5_7b_chat, turbomind_internlm2_5_20b_chat, turbomind_internlm2_5_20b_chat_4bits, turbomind_internlm2_5_20b_chat_kvint4, pt_internlm2_5_20b_chat, turbomind_llama_3d1_8b_instruct, pt_llama_3d1_8b_instruct, turbomind_llama_3d1_8b_instruct_4bits, turbomind_llama_3d1_8b_instruct_kvint4, turbomind_qwen2_7b_instruct, turbomind_qwen2_7b_instruct_4bits, pt_qwen1_5_moe_2_7b_chat, pt_gemma_2_9b_it]" "[*race_datasets, *gsm8k_datasets]" /root/evaluation-reports/${{ github.run_id }} chat true
- name: Clear workspace
if: always()
run: |
export workdir=$(pwd)
cd ..
rm -rf $workdir
mkdir $workdir
chmod -R 777 $workdir
get_benchmark_result:
if: ${{!cancelled() && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'benchmark'))}}
needs: [test_benchmark]
timeout-minutes: 5
runs-on: [self-hosted, linux-a100]
env:
BENCHMARK_REPORT_DIR: /nvme/qa_test_models/benchmark-reports/${{ github.run_id }}
steps:
- name: Clone repository
uses: actions/checkout@v3
with:
repository: ${{ github.event.inputs.repo_org || 'InternLM/lmdeploy' }}
ref: ${{github.event.inputs.repo_ref || 'main'}}
- name: Get overview
run: |
pip install pandas fire mmengine
python3 .github/scripts/action_tools.py generate_benchmark_report $BENCHMARK_REPORT_DIR
get_coverage_report:
if: ${{!cancelled()}}
runs-on: [self-hosted, linux-a100]
needs: [test_tools, test_restful, test_pipeline, test_benchmark]
timeout-minutes: 5
container:
image: openmmlab/lmdeploy:latest-cu11
options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
volumes:
- /nvme/github-actions/pip-cache:/root/.cache/pip
- /nvme/github-actions/packages:/root/packages
- /nvme/qa_test_models:/nvme/qa_test_models
- /usr/share/zoneinfo/Asia/Shanghai:/etc/localtime:ro
steps:
- name: Copy repository and Artifacts
run: cp -r ${{env.TEST_CODE_PATH}}/. .
- name: Install lmdeploy
run: |
python3 -m pip install lmdeploy-*.whl --no-deps
python3 -m pip install -r requirements/test.txt
- name: Get coverage report
run: |
pip install coverage
coverage combine ${{env.REPORT_DIR}}
coverage xml -o ${{env.REPORT_DIR}}/coverage.xml
coverage report -m
mv .coverage ${{env.REPORT_DIR}}/.coverage
- name: Clear workfile
if: always()
run: |
chmod -R 777 $REPORT_DIR
export workdir=$(pwd)
cd ..
rm -rf $workdir
mkdir $workdir
chmod -R 777 $workdir
notify_to_feishu:
if: always() && !cancelled() && (github.ref_name == 'develop' || github.ref_name == 'main')
needs: [get_benchmark_result, get_coverage_report, test_evaluation]
timeout-minutes: 5
runs-on: [self-hosted, linux-a100]
steps:
- name: notify
if: contains(needs.*.result, 'failure')
run: |
curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"Lmdeploy- Daily test finished!!!","content":[[{"tag":"text","text":"branch: ${{github.ref_name}}, run action: ${{github.workflow}} failed. "},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.FEISHU_USER_ID }}'"}]]}}}}' ${{ secrets.FEISHU_WEBHOOK_URL }}