Merge remote-tracking branch 'origin/main' into slow

irexyc · Sep 5, 2024 · 58114d5 · 58114d5
2 parents ce298ab + 4866410
commit 58114d5
Show file tree

Hide file tree

Showing 131 changed files with 2,388 additions and 2,151 deletions.
diff --git a/.github/workflows/cuda11.8-whl-release.yml b/.github/workflows/cuda11.8-whl-release.yml
@@ -46,11 +46,12 @@ jobs:
           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} ${OUTPUT_FOLDER}
       - name: Upload Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           if-no-files-found: error
           path: builder/manywheel/${{ env.OUTPUT_FOLDER }}/*
           retention-days: 1
+          name: linux-${{ matrix.pyver }}
 
   windows-build:
     strategy:
@@ -89,11 +90,12 @@ jobs:
           rm build -Force -Recurse
           python setup.py bdist_wheel -d build/wheel
       - name: Upload Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           if-no-files-found: error
           path: build/wheel/*
           retention-days: 1
+          name: windows-${{ matrix.pyver }}
 
   publish:
     runs-on: ubuntu-latest
@@ -105,11 +107,15 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v3
       - name: Download artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
+        with:
+          path: artifact
+          merge-multiple: true
       - name: Add cuda version to package name
         run: |
           ver=$(cat lmdeploy/version.py | grep '__version__ =' | cut -d\' -f2)
           cuver=$ver+cu118
+          ls -lh
           cd artifact
           for file in *; do
             mv "$file" "`echo $file | sed "s/$ver/$cuver/g"`";

diff --git a/.github/workflows/daily_ete_test.yml b/.github/workflows/daily_ete_test.yml
diff --git a/.github/workflows/evaluate.yml b/.github/workflows/evaluate.yml
@@ -113,13 +113,13 @@ jobs:
       - name: Install pytorch
         run: |
           python3 -m pip cache dir
-          python3 -m pip install torch==2.2.2 torchvision==0.17.2 --index-url https://download.pytorch.org/whl/cu118
+          python3 -m pip install torch==2.3.0 torchvision==0.18.0 --index-url https://download.pytorch.org/whl/cu118
       - 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-2.5.7+cu118torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
-          python3 -m pip install -U 'xformers<=0.0.26' --index-url https://download.pytorch.org/whl/cu118
+          python3 -m pip install /root/packages/flash_attn-2.6.3+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
+          python3 -m pip install /root/packages/xformers-0.0.27+cu118-cp310-cp310-manylinux2014_x86_64.whl --no-deps
           python3 -m pip install ${{env.dependency_pkgs}}
       - name: Install lmdeploy
         run: |

diff --git a/.github/workflows/pr_ete_test.yml b/.github/workflows/pr_ete_test.yml
@@ -45,7 +45,8 @@ jobs:
     steps:
       - name: Setup systems
         run: |
-          rm /etc/apt/sources.list.d/cuda*.list && apt-get update -y && apt-get install -y software-properties-common wget vim &&\
+          apt-get update -y && apt-get install -y software-properties-common wget vim git curl &&\
+          curl https://sh.rustup.rs -sSf | sh -s -- -y &&\
           add-apt-repository ppa:deadsnakes/ppa -y && apt-get update -y && apt-get install -y --no-install-recommends \
           ninja-build rapidjson-dev libgoogle-glog-dev gdb python3.10 python3.10-dev python3.10-venv \
           && apt-get clean -y && rm -rf /var/lib/apt/lists/* && cd /opt && python3 -m venv py3

diff --git a/.github/workflows/pypi.yml b/.github/workflows/pypi.yml
@@ -45,11 +45,12 @@ jobs:
           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} ${OUTPUT_FOLDER}
       - name: Upload Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           if-no-files-found: error
           path: builder/manywheel/${{ env.OUTPUT_FOLDER }}/*
           retention-days: 1
+          name: linux-${{ matrix.pyver }}
 
   windows-build:
     strategy:
@@ -90,11 +91,12 @@ jobs:
           rm build -Force -Recurse
           python setup.py bdist_wheel -d build/wheel
       - name: Upload Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           if-no-files-found: error
           path: build/wheel/*
           retention-days: 1
+          name: windows-${{ matrix.pyver }}
 
   publish:
     runs-on: ubuntu-latest
@@ -104,7 +106,10 @@ jobs:
       - windows-build
     steps:
       - name: Download artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
+        with:
+          path: artifact
+          merge-multiple: true
       - name: Display artifacts
         run: ls artifact/ -lh
       - name: Set up python3.8

diff --git a/.github/workflows/stable.yml b/.github/workflows/stable.yml
@@ -78,7 +78,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        model: ['internlm/internlm2-chat-20b']
+        model: ['internlm/internlm2_5-20b-chat']
     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 -e NO_PROXY=localhost,127.0.0.1 -e no_proxy=localhost,127.0.0.1 --pull never"
@@ -134,10 +134,10 @@ jobs:
           sleep 120s
       - name: Test lmdeploy - restful api
         run: |
-          python3 benchmark/profile_restful_api.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/ShareGPT_V3_unfiltered_cleaned_split.json --stream-output True --num-prompts 10000 --csv ${{env.REPORT_DIR}}/stable.csv > ${{env.REPORT_DIR}}/stable.log
-          python3 /nvme/qa_test_models/offline_pkg/profile_restful_api_internal.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/Mixed.json --stream-output True --num-prompts 100000 --csv ${{env.REPORT_DIR}}/stable-internal-1.csv > ${{env.REPORT_DIR}}/stable-internal-1.log
-          python3 /nvme/qa_test_models/offline_pkg/profile_restful_api_internal.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/Mixed.json --stream-output True --num-prompts 100000 --csv ${{env.REPORT_DIR}}/stable-internal-2.csv > ${{env.REPORT_DIR}}/stable-internal-2.log
-          python3 /nvme/qa_test_models/offline_pkg/profile_restful_api_internal.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/Mixed.json --stream-output True --num-prompts 100000 --csv ${{env.REPORT_DIR}}/stable-internal-2.csv > ${{env.REPORT_DIR}}/stable-internal-3.log
+          python3 benchmark/profile_restful_api.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/ShareGPT_V3_unfiltered_cleaned_split.json --stream-output True --num-prompts 10000 --csv ${{env.REPORT_DIR}}/stable.csv &> ${{env.REPORT_DIR}}/stable.log
+          python3 /nvme/qa_test_models/offline_pkg/profile_restful_api_internal.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/Mixed.json --stream-output True --num-prompts 100000 --csv ${{env.REPORT_DIR}}/stable-internal-1.csv &> ${{env.REPORT_DIR}}/stable-internal-1.log
+          python3 /nvme/qa_test_models/offline_pkg/profile_restful_api_internal.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/Mixed.json --stream-output True --num-prompts 100000 --csv ${{env.REPORT_DIR}}/stable-internal-2.csv &> ${{env.REPORT_DIR}}/stable-internal-2.log
+          python3 /nvme/qa_test_models/offline_pkg/profile_restful_api_internal.py localhost:23344 /nvme/qa_test_models/${{matrix.model}} /nvme/qa_test_models/datasets/Mixed.json --stream-output True --num-prompts 100000 --csv ${{env.REPORT_DIR}}/stable-internal-3.csv &> ${{env.REPORT_DIR}}/stable-internal-3.log
       - name: Kill api server
         if: always()
         run: |

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -44,7 +44,8 @@ repos:
     rev: v2.1.0
     hooks:
       - id: codespell
-        args: ["--skip=third_party/*,*.ipynb,*.proto,src/turbomind/kernels/gemm/transform.h"]
+        args: ["--skip=third_party/*,*.ipynb,*.proto,src/turbomind/kernels/gemm/transform.h,docker/Dockerfile_aarch64_ascend,docs/en/get_started/ascend/get_started.md,docs/zh_cn/get_started/ascend/get_started.md"]
+
 
   - repo: https://github.com/myint/docformatter
     rev: v1.4