[ci] add h800 function test workflow

.github/workflows/benchmark.yml

@@ -27,7 +27,7 @@ on:
 env:
   HOST_PIP_CACHE_DIR: /nvme/github-actions/pip-cache
   HOST_LOCALTIME: /usr/share/zoneinfo/Asia/Shanghai
-  OUTPUT_FOLDER: cuda11.8_dist_${{ github.run_id }}
+  OUTPUT_FOLDER: cuda12.4_dist_${{ github.run_id }}
   REPORT_DIR: /nvme/qa_test_models/benchmark-reports/${{ github.run_id }}
   ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
   FAIL_CONFIG: ${{ github.run_attempt != 1 && '--lf --lfnf none' || '--lf'}}
@@ -42,7 +42,7 @@ jobs:
     env:
       PYTHON_VERSION: ${{ matrix.pyver }}
       PLAT_NAME: manylinux2014_x86_64
-      DOCKER_TAG: cuda11.8
+      DOCKER_TAG: cuda12.4
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
@@ -108,7 +108,7 @@ jobs:
       - name: Install lmdeploy
         if: ${{github.event_name == 'schedule' || !inputs.offline_mode}}
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install -r requirements/test.txt
       - name: Install lmdeploy - offline
         if: ${{inputs.offline_mode}}

.github/workflows/daily_ete_test.yml

@@ -44,7 +44,7 @@ on:
 env:
   HOST_PIP_CACHE_DIR: /nvme/github-actions/pip-cache
   HOST_LOCALTIME: /usr/share/zoneinfo/Asia/Shanghai
-  OUTPUT_FOLDER: cuda11.8_dist_${{ github.run_id }}
+  OUTPUT_FOLDER: cuda12.4_dist_${{ 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
@@ -64,7 +64,7 @@ jobs:
     env:
       PYTHON_VERSION: ${{ matrix.pyver }}
       PLAT_NAME: manylinux2014_x86_64
-      DOCKER_TAG: cuda11.8
+      DOCKER_TAG: cuda12.4
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
@@ -96,7 +96,7 @@ jobs:
     runs-on: [self-hosted, linux-a100]
     timeout-minutes: 50
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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
@@ -136,7 +136,7 @@ jobs:
       MODELSCOPE_CACHE: /nvme/qa_test_models/modelscope_hub
       MODELSCOPE_MODULES_CACHE: /nvme/qa_test_models/modelscope_modules
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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
@@ -168,7 +168,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test lmdeploy - quantization w4a16
         continue-on-error: true
@@ -219,7 +219,7 @@ jobs:
       MODELSCOPE_CACHE: /nvme/qa_test_models/modelscope_hub
       MODELSCOPE_MODULES_CACHE: /nvme/qa_test_models/modelscope_modules
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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
@@ -251,7 +251,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test lmdeploy - chat
         continue-on-error: true
@@ -324,7 +324,7 @@ jobs:
             model: Intern-S1
     timeout-minutes: 60
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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
@@ -352,7 +352,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Start restful api
         if:  matrix.model != 'internlm2_5-20b'
@@ -408,7 +408,7 @@ jobs:
     needs: test_quantization
     timeout-minutes: 120
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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
@@ -436,7 +436,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test lmdeploy - interface pipeline case
         run: |
@@ -465,7 +465,7 @@ jobs:
     needs: test_quantization
     timeout-minutes: 120
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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
@@ -493,7 +493,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test benchmark script
         run: |
@@ -520,7 +520,7 @@ jobs:
       matrix:
         evaluate_type: ['chat', 'base']
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip -e NVIDIA_DISABLE_REQUIRE=1 --pull never"
       volumes:
         - /nvme/github-actions/pip-cache:/root/.cache/pip
@@ -550,8 +550,7 @@ jobs:
         run: |
           git clone --depth=1 https://github.com/open-compass/opencompass.git
           cd opencompass
-          cp /nvme/qa_test_models/offline_pkg/requirements-oc.txt requirements/runtime.txt
-          python3 -m pip install -e .
+          python3 -m pip install .
           echo "OPENCOMPASS_DIR=$(pwd)" >> $GITHUB_ENV
       - name: Check env
         run: |
@@ -560,7 +559,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Setup paths for evaluation
         run: |
@@ -571,7 +570,7 @@ jobs:
         run: |
           export LMDEPLOY_DIR=$(pwd)
 
-          python3 .github/scripts/action_tools.py evaluate "[turbomind_internlm2_5_7b_chat, pytorch_internlm2_5_7b_chat, turbomind_internlm2_5_7b_chat_batch1, turbomind_internlm2_5_7b_chat_batch1_4bits, turbomind_internlm3_8b_instruct, pytorch_internlm3_8b_instruct, turbomind_internlm2_5_20b_chat, pytorch_internlm2_5_20b_chat, turbomind_qwen1_5_7b_chat, pytorch_qwen1_5_7b_chat, turbomind_llama3_8b_instruct, pytorch_llama3_8b_instruct, turbomind_llama3_1_8b_instruct, pytorch_llama3_1_8b_instruct, turbomind_qwen2_7b_instruct, pytorch_qwen2_7b_instruct, turbomind_qwen2_5_7b_instruct, pytorch_qwen2_5_7b_instruct, turbomind_llama2_7b_chat, pytorch_qwen1_5_moe_2_7b_chat, pytorch_gemma_2_9b_it, pytorch_gemma_2_27b_it]" "[*race_datasets, *gsm8k_datasets, *ifeval_datasets]" /root/evaluation-reports/${{ github.run_id }} chat true
+          python3 .github/scripts/action_tools.py evaluate "[turbomind_internlm2_5_7b_chat, pytorch_internlm2_5_7b_chat, turbomind_internlm2_5_7b_chat_batch1, turbomind_internlm2_5_7b_chat_batch1_4bits, turbomind_internlm3_8b_instruct, pytorch_internlm3_8b_instruct, turbomind_internlm2_5_20b_chat, pytorch_internlm2_5_20b_chat, turbomind_qwen1_5_7b_chat, pytorch_qwen1_5_7b_chat, turbomind_llama3_8b_instruct, pytorch_llama3_8b_instruct, turbomind_llama3_1_8b_instruct, pytorch_llama3_1_8b_instruct, turbomind_qwen2_5_7b_instruct, pytorch_qwen2_5_7b_instruct, turbomind_llama2_7b_chat, pytorch_qwen1_5_moe_2_7b_chat, pytorch_gemma_2_9b_it, pytorch_gemma_2_27b_it]" "[*race_datasets, *gsm8k_datasets, *ifeval_datasets]" /root/evaluation-reports/${{ github.run_id }} chat true
       - name: Evaluate base models
         if: matrix.evaluate_type == 'base'
         run: |
@@ -594,7 +593,7 @@ jobs:
     timeout-minutes: 5
     runs-on: [self-hosted, linux-a100]
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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
@@ -619,7 +618,7 @@ jobs:
     needs: [test_tools, test_restful, test_pipeline, test_benchmark]
     timeout-minutes: 5
     container:
-      image: openmmlab/lmdeploy:latest-cu12.8
+      image: openmmlab/lmdeploy:latest-cu12
       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

.github/workflows/daily_ete_test_3090.yml

@@ -153,7 +153,7 @@ jobs:
           python3 -m pip install -r requirements/lite.txt
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install transformers==4.53.1 datasets==3.6.0 timm
           python3 -m pip install -r requirements/test.txt
       - name: Check env
@@ -163,7 +163,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test lmdeploy - quantization w4a16
         continue-on-error: true
@@ -226,7 +226,7 @@ jobs:
           python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install -r requirements/test.txt
       - name: Check env
         run: |
@@ -235,7 +235,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test lmdeploy - chat
         continue-on-error: true
@@ -290,7 +290,7 @@ jobs:
           python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install -r requirements/test.txt
       - name: Check env
         run: |
@@ -299,7 +299,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Start restful api turbomind
         if: matrix.backend == 'turbomind'
@@ -370,7 +370,7 @@ jobs:
         run: cp -r ${{env.TEST_CODE_PATH}}/. .
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install -r requirements/test.txt
       - name: Get coverage report
         run: |

.github/workflows/daily_ete_test_5080.yml

@@ -92,7 +92,7 @@ jobs:
   download_pkgs:
     needs: linux-build
     if: ${{!cancelled()}}
-    runs-on: [self-hosted, 5090-r1]
+    runs-on: [self-hosted, 5080-r1]
     timeout-minutes: 50
     container:
       image: openmmlab/lmdeploy:latest-cu12.8
@@ -129,7 +129,7 @@ jobs:
   test_quantization:
     needs: download_pkgs
     if: ${{!cancelled() && contains(needs.download_pkgs.result, 'success') && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'quant') )}}
-    runs-on: [self-hosted, 5090-r1]
+    runs-on: [self-hosted, 5080-r1]
     timeout-minutes: 150
     env:
       PYTHONPATH: /nvme/qa_test_models/offline_pkg/LLaVA
@@ -153,7 +153,7 @@ jobs:
           python3 -m pip install -r requirements/lite.txt
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install transformers==4.53.1 datasets==3.6.0 timm
           python3 -m pip install -r requirements/test.txt
       - name: Check env
@@ -163,7 +163,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test lmdeploy - quantization w4a16
         continue-on-error: true
@@ -188,7 +188,7 @@ jobs:
           chmod -R 777 $workdir
   test_tools:
     if: ${{!cancelled() && !contains(needs.test_quantization.result, 'fail') && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'tools'))}}
-    runs-on: [self-hosted, 5090-r1]
+    runs-on: [self-hosted, 5080-r1]
     needs: test_quantization
     timeout-minutes: 300
     strategy:
@@ -225,7 +225,7 @@ jobs:
           python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install -r requirements/test.txt
       - name: Check env
         run: |
@@ -234,7 +234,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Test lmdeploy - chat
         continue-on-error: true
@@ -265,7 +265,7 @@ jobs:
           chmod -R 777 $workdir
   test_restful:
     if: ${{!cancelled() && !contains(needs.test_quantization.result, 'fail') && (github.event_name == 'schedule' || contains(fromJSON(github.event.inputs.regression_func), 'restful'))}}
-    runs-on: [self-hosted, 5090-r1]
+    runs-on: [self-hosted, 5080-r1]
     needs: test_quantization
     strategy:
       fail-fast: false
@@ -289,7 +289,7 @@ jobs:
           python3 -m pip install -r ${{env.OFFLINE_REQUIREMENTS}}
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install -r requirements/test.txt
       - name: Check env
         run: |
@@ -298,7 +298,7 @@ jobs:
           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
+          mkdir ${{env.REPORT_DIR}}/.pytest_cache -p && rm autotest/.pytest_cache -f
           ln -s ${{env.REPORT_DIR}}/.pytest_cache autotest
       - name: Start restful api turbomind
         if: matrix.backend == 'turbomind'
@@ -353,7 +353,7 @@ jobs:
           chmod -R 777 $workdir
   get_coverage_report:
     if: ${{!cancelled() && success()}}
-    runs-on: [self-hosted, 5090-r1]
+    runs-on: [self-hosted, 5080-r1]
     needs: [test_tools, test_restful]
     timeout-minutes: 5
     container:
@@ -368,7 +368,7 @@ jobs:
         run: cp -r ${{env.TEST_CODE_PATH}}/. .
       - name: Install lmdeploy
         run: |
-          python3 -m pip install lmdeploy-*.whl --no-deps
+          python3 -m pip uninstall lmdeploy -y && python3 -m pip install lmdeploy-*.whl --no-deps
           python3 -m pip install -r requirements/test.txt
       - name: Get coverage report
         run: |