[CI] add ascend test #3959
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,171 @@ | ||
| name: daily_ete_test_ascend | ||
|
|
||
| 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: "['pytorch']" | ||
| model: | ||
| required: true | ||
| description: 'Set testcase module filter: llm, vllm. Default contains all models' | ||
| type: string | ||
| default: "['llm']" | ||
| function: | ||
| required: true | ||
| description: 'Set testcase function filter: chat, restful, pipeline. Default contains all functions' | ||
| type: string | ||
| default: '["pipeline", "restful", "chat"]' | ||
| regression_func: | ||
| required: true | ||
| description: 'regression functions' | ||
| type: string | ||
| default: "['tools']" | ||
|
|
||
| env: | ||
| REPORT_DIR: /test/test-reports/${{ github.run_id }} | ||
| COV_PARAM: --cov /usr/local/python3.10.17/lib/python3.10/site-packages/lmdeploy | ||
| FAIL_CONFIG: ${{ github.event_name == 'push' && github.run_attempt != 1 && '--lf --lfnf none' || '--lf'}} | ||
| TEST_CODE_PATH: /test/test_pkg/lmdeploy/${{ github.run_id }} | ||
| LOG_PATH: /test/log/${{ github.run_id }} | ||
| TMPDIR: /mnt/deeplink/docker-tmp/qa_tmp | ||
| RAY_TMPDIR: /mnt/deeplink/docker-tmp/qa_tmp/ray | ||
|
|
||
| jobs: | ||
| download_pkgs: | ||
| if: ${{!cancelled()}} | ||
| runs-on: [self-hosted, ascend-013] | ||
| timeout-minutes: 50 | ||
| container: | ||
| image: crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:910b-latest | ||
| options: "--device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 --device=/dev/davinci4 --device=/dev/davinci5 --device=/dev/davinci6 --device=/dev/davinci7 --device=/dev/davinci_manager --device=/dev/devmm_svm --device=/dev/hisi_hdc -e PIP_CACHE_DIR=/root/.cache/pip --shm-size=150g --pull never" | ||
| volumes: | ||
| - /usr/local/Ascend/driver:/usr/local/Ascend/driver:ro | ||
| - /usr/local/sbin:/usr/local/sbin:ro | ||
| - /var/log/npu/slog:/var/log/npu/slog | ||
| - /var/log/npu/profiling:/var/log/npu/profiling | ||
| - /var/log/npu/dump:/var/log/npu/dump | ||
| - /var/log/npu:/usr/slog | ||
| - /etc/hccn.conf:/etc/hccn.conf:ro | ||
| - /root/qa_test:/test | ||
| - /mnt:/mnt | ||
| - /root/.cache/pip:/root/.cache/pip | ||
| steps: | ||
| - name: Clone repository | ||
| uses: actions/checkout@v2 | ||
| if: ${{ !cancelled() }} | ||
| with: | ||
| repository: ${{ github.event.inputs.repo_org || 'InternLM/lmdeploy' }} | ||
| ref: ${{github.event.inputs.repo_ref || 'main'}} | ||
| - name: Copy repository | ||
| if: ${{ !cancelled() }} | ||
| run: rm -rf ${{env.TEST_CODE_PATH}} && mkdir ${{env.TEST_CODE_PATH}} && cp -r . ${{env.TEST_CODE_PATH}} | ||
|
|
||
| test_tools: | ||
| if: ${{!cancelled() && contains(fromJSON(github.event.inputs.regression_func), 'tools')}} | ||
| runs-on: [self-hosted, ascend-013] | ||
| needs: download_pkgs | ||
| timeout-minutes: 300 | ||
| strategy: | ||
| fail-fast: false | ||
| matrix: | ||
| backend: ${{ fromJSON(inputs.backend || '["turbomind", "pytorch"]')}} | ||
| model: ${{ fromJSON(inputs.model || '["llm", "mllm"]')}} | ||
| function: ${{ fromJSON(inputs.function || '["pipeline","restful","chat"]')}} | ||
| exclude: | ||
| - backend: turbomind | ||
| model: mllm | ||
| function: chat | ||
| - backend: pytorch | ||
| model: mllm | ||
| function: chat | ||
| container: | ||
| image: crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:910b-latest | ||
| options: "--device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 --device=/dev/davinci4 --device=/dev/davinci5 --device=/dev/davinci6 --device=/dev/davinci7 --device=/dev/davinci_manager --device=/dev/devmm_svm --device=/dev/hisi_hdc -e PIP_CACHE_DIR=/root/.cache/pip --shm-size=150g --pull never" | ||
| volumes: | ||
| - /usr/local/Ascend/driver:/usr/local/Ascend/driver | ||
| - /usr/local/sbin:/usr/local/sbin | ||
| - /var/log/npu/slog:/var/log/npu/slog | ||
| - /var/log/npu/profiling:/var/log/npu/profiling | ||
| - /var/log/npu/dump:/var/log/npu/dump | ||
| - /var/log/npu:/usr/slog | ||
| - /etc/hccn.conf:/etc/hccn.conf | ||
| - /root/qa_test:/test | ||
| - /mnt:/mnt | ||
| - /root/.cache/pip:/root/.cache/pip | ||
| steps: | ||
| - name: Copy repository and Artifacts | ||
| run: | | ||
| cp -r ${{ env.TEST_CODE_PATH }}/. . | ||
| - name: Install lmdeploy - offline | ||
| run: | | ||
| python3 -m pip install -r requirements_ascend.txt -i https://mirrors.aliyun.com/pypi/simple/ | ||
| - name: Install lmdeploy - test | ||
| run: | | ||
| python3 -m pip install -r requirements/test.txt -i https://mirrors.aliyun.com/pypi/simple/ | ||
| - name: Check env | ||
| run: | | ||
| python3 -m pip list | ||
| lmdeploy check_env | ||
| rm -rf allure-results | ||
| # remove tmp log in testcase | ||
| rm -rf ${{ env.LOG_PATH }}/* | ||
| mkdir ${{ env.REPORT_DIR }}/.pytest_cache -p | ||
| ln -s ${{ env.REPORT_DIR }}/.pytest_cache autotest | ||
| - name: Test lmdeploy - chat | ||
| continue-on-error: true | ||
| if: ${{ (matrix.backend == 'pytorch' || matrix.backend == 'turbomind') && matrix.model == 'llm' && matrix.function == 'chat' }} | ||
| run: | | ||
| pytest autotest/tools/chat/test_command_chat_hf_${{ matrix.backend }}.py -m 'gpu_num_1 and test_ascend' -n 8 --device ascend --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_${{ matrix.backend }}.py -m 'gpu_num_2 and test_ascend' -n 4 --device ascend --alluredir=${{ env.REPORT_DIR }} ${{ env.COV_PARAM }} || true | ||
| mv .coverage ${{ env.REPORT_DIR }}/.coverage.$(date +'%Y%m%d%H%M%S') | ||
| pytest autotest/tools/chat/test_command_chat_hf_${{ matrix.backend }}.py -m 'gpu_num_4 and test_ascend' -n 2 --device ascend --alluredir=${{ env.REPORT_DIR }} ${{ env.COV_PARAM }} || true | ||
| mv .coverage ${{ env.REPORT_DIR }}/.coverage.$(date +'%Y%m%d%H%M%S') | ||
| pytest autotest/tools/chat/test_command_chat_hf_${{ matrix.backend }}.py -m 'gpu_num_8 and test_ascend' --device ascend --alluredir=${{ 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: ${{ matrix.function == 'pipeline' }} | ||
| run: | | ||
| pytest autotest/tools/pipeline/test_pipeline_chat_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_1 and test_ascend' -n 8 --device ascend --alluredir=${{ 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_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_2 and test_ascend' -n 4 --device ascend --alluredir=${{ env.REPORT_DIR }} ${{ env.COV_PARAM }} || true | ||
| mv .coverage ${{ env.REPORT_DIR }}/.coverage.$(date +'%Y%m%d%H%M%S') | ||
| pytest autotest/tools/pipeline/test_pipeline_chat_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_4 and test_ascend' -n 2 --device ascend --alluredir=${{ env.REPORT_DIR }} ${{ env.COV_PARAM }} || true | ||
| mv .coverage ${{ env.REPORT_DIR }}/.coverage.$(date +'%Y%m%d%H%M%S') | ||
| pytest autotest/tools/pipeline/test_pipeline_chat_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_8 and test_ascend' --device ascend --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: ${{ matrix.function == 'restful' }} | ||
| run: | | ||
| pytest autotest/tools/restful/test_restful_chat_hf_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_1 and test_ascend' -n 8 --device ascend --alluredir=${{ 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_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_2 and test_ascend' -n 4 --device ascend --alluredir=${{ env.REPORT_DIR }} ${{ env.COV_PARAM }} || true | ||
| mv .coverage ${{ env.REPORT_DIR }}/.coverage.$(date +'%Y%m%d%H%M%S') | ||
| pytest autotest/tools/restful/test_restful_chat_hf_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_4 and test_ascend' -n 2 --device ascend --alluredir=${{ env.REPORT_DIR }} ${{ env.COV_PARAM }} || true | ||
| mv .coverage ${{ env.REPORT_DIR }}/.coverage.$(date +'%Y%m%d%H%M%S') | ||
| pytest autotest/tools/restful/test_restful_chat_hf_${{ matrix.backend }}_${{ matrix.model }}.py -m 'gpu_num_8 and test_ascend' --device ascend --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 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,35 @@ | ||
| model_path: /mnt/deeplink/group01/deeplink-test/weight | ||
| resource_path: /nvme/qa_test_models/resource | ||
| dst_path: /nvme/qa_test_models/autotest_model | ||
| log_path: /test/log | ||
| benchmark_path: /nvme/qa_test_models/benchmark-reports | ||
| dataset_path: /nvme/qa_test_models/datasets/ShareGPT_V3_unfiltered_cleaned_split.json | ||
| env_tag: a100 | ||
|
|
||
| tp_config: | ||
| Qwen2.5-32B-Instruct: 2 | ||
|
|
||
| pytorch_chat_model: | ||
| - /Qwen3-0.6B | ||
|
|
||
| pytorch_vl_model: | ||
| - /Qwen3-0.6B | ||
|
|
||
| pytorch_base_model: | ||
| - /Qwen3-0.6B | ||
|
|
||
| pytorch_quatization: | ||
| awq: | ||
| - meta-llama/Meta-Llama-3-8B-Instruct | ||
| w8a8: | ||
| - meta-llama/Meta-Llama-3-8B-Instruct | ||
| no_kvint4: | ||
| - /Qwen3-0.6B | ||
| no_kvint8: | ||
| - /Qwen3-0.6B | ||
|
||
|
|
||
| longtext_model: | ||
| - /Qwen3-0.6B | ||
zhulinJulia24 marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
|
|
||
| benchmark_model: | ||
| - /Qwen3-0.6B | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What's this tag used for?