Merge branch 'main' into qwen2audio_new

.buildkite/lm-eval-harness/configs/Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml

@@ -0,0 +1,11 @@
+# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8 -b "auto" -l 1000 -f 5 -t 1
+model_name: "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8"
+tasks:
+- name: "gsm8k"
+  metrics:
+  - name: "exact_match,strict-match"
+    value: 0.356
+  - name: "exact_match,flexible-extract"
+    value: 0.358
+limit: 1000
+num_fewshot: 5

.buildkite/lm-eval-harness/configs/models-small.txt

@@ -1,6 +1,6 @@
 Meta-Llama-3-8B-Instruct.yaml
 Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml
-Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.yaml
+Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml
 Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml
 Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
 Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml

.buildkite/test-pipeline.yaml

@@ -310,13 +310,22 @@ steps:
     - pytest -v -s models/test_oot_registration.py # it needs a clean process
     - pytest -v -s models/*.py --ignore=models/test_oot_registration.py
 
-- label: Decoder-only Language Models Test # 1h36min
+- label: Decoder-only Language Models Test (Standard) # 35min
   #mirror_hardwares: [amd]
   source_file_dependencies:
   - vllm/
   - tests/models/decoder_only/language
   commands:
-    - pytest -v -s models/decoder_only/language
+    - pytest -v -s models/decoder_only/language/test_models.py
+    - pytest -v -s models/decoder_only/language/test_big_models.py
+
+- label: Decoder-only Language Models Test (Extended) # 1h20min
+  nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/decoder_only/language
+  commands:
+    - pytest -v -s models/decoder_only/language --ignore=models/decoder_only/language/test_models.py --ignore=models/decoder_only/language/test_big_models.py
 
 - label: Decoder-only Multi-Modal Models Test # 1h31min
   #mirror_hardwares: [amd]

.github/workflows/actionlint.yml

@@ -34,4 +34,5 @@ jobs:
 
       - name: "Run actionlint"
         run: |
+          echo "::add-matcher::.github/workflows/matchers/actionlint.json"
           tools/actionlint.sh -color

.github/workflows/add_label_automerge.yml

@@ -8,7 +8,7 @@ jobs:
         runs-on: ubuntu-latest
         steps:
             -   name: Add label
-                uses: actions/github-script@v7
+                uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
                 with:
                     script: |
                         github.rest.issues.addLabels({

.github/workflows/clang-format.yml

@@ -17,9 +17,9 @@ jobs:
       matrix:
         python-version: ["3.11"]
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
@@ -38,4 +38,4 @@ jobs:
         )
         find csrc/ \( -name '*.h' -o -name '*.cpp' -o -name '*.cu' -o -name '*.cuh' \) -print \
             | grep -vFf <(printf "%s\n" "${EXCLUDES[@]}") \
-            | xargs clang-format --dry-run --Werror
+            | xargs clang-format --dry-run --Werror

.github/workflows/matchers/mypy.json

@@ -0,0 +1,16 @@
+{
+  "problemMatcher": [
+    {
+      "owner": "mypy",
+      "pattern": [
+        {
+          "regexp": "^(.+):(\\d+):\\s(error|warning):\\s(.+)$",
+          "file": 1,
+          "line": 2,
+          "severity": 3,
+          "message": 4
+        }
+      ]
+    }
+  ]
+}

.github/workflows/matchers/ruff.json

@@ -0,0 +1,17 @@
+{
+    "problemMatcher": [
+      {
+        "owner": "ruff",
+        "pattern": [
+          {
+            "regexp": "^(.+?):(\\d+):(\\d+): (\\w+): (.+)$",
+            "file": 1,
+            "line": 2,
+            "column": 3,
+            "code": 4,
+            "message": 5
+          }
+        ]
+      }
+    ]
+  }

.github/workflows/mypy.yaml

@@ -17,9 +17,9 @@ jobs:
       matrix:
         python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
@@ -32,4 +32,5 @@ jobs:
         pip install types-setuptools
     - name: Mypy
       run: |
-        tools/mypy.sh
+        echo "::add-matcher::.github/workflows/matchers/mypy.json"
+        tools/mypy.sh 1

.github/workflows/publish.yml

@@ -21,7 +21,7 @@ jobs:
       upload_url: ${{ steps.create_release.outputs.upload_url }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
 
       - name: Extract branch info
         shell: bash
@@ -30,7 +30,7 @@ jobs:
 
       - name: Create Release
         id: create_release
-        uses: "actions/github-script@v7"
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         env:
           RELEASE_TAG: ${{ env.release_tag }}
         with:
@@ -54,10 +54,10 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
 
       - name: Setup ccache
-        uses: hendrikmuhs/[email protected]
+        uses: hendrikmuhs/ccache-action@ed74d11c0b343532753ecead8a951bb09bb34bc9 # v1.2.14
         with:
           create-symlink: true
           key: ${{ github.job }}-${{ matrix.python-version }}-${{ matrix.cuda-version }}
@@ -68,7 +68,7 @@ jobs:
           bash -x .github/workflows/scripts/env.sh
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
         with:
             python-version: ${{ matrix.python-version }}
 
@@ -92,7 +92,7 @@ jobs:
           echo "asset_name=${asset_name}" >> "$GITHUB_ENV"
 
       - name: Upload Release Asset
-        uses: actions/upload-release-asset@v1
+        uses: actions/upload-release-asset@e8f9f06c4b078e705bd2ea027f0926603fc9b4d5 # v1.0.2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:

.github/workflows/reminder_comment.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Remind to run full CI on PR
-        uses: actions/github-script@v7
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
           script: |
             github.rest.issues.createComment({

.github/workflows/ruff.yml

@@ -17,9 +17,9 @@ jobs:
       matrix:
         python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
@@ -28,7 +28,8 @@ jobs:
         pip install -r requirements-lint.txt
     - name: Analysing the code with ruff
       run: |
-        ruff check .
+        echo "::add-matcher::.github/workflows/matchers/ruff.json"
+        ruff check --output-format github .
     - name: Spelling check with codespell
       run: |
         codespell --toml pyproject.toml

.github/workflows/yapf.yml

@@ -16,9 +16,9 @@ jobs:
       matrix:
         python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

CMakeLists.txt

@@ -169,12 +169,12 @@ endif()
 
 #
 # Use FetchContent for C++ dependencies that are compiled as part of vLLM's build process.
-# Configure it to place files in vllm/.deps, in order to play nicely with sccache.
+# setup.py will override FETCHCONTENT_BASE_DIR to play nicely with sccache.
+# Each dependency that produces build artifacts should override its BINARY_DIR to avoid
+# conflicts between build types. It should instead be set to ${CMAKE_BINARY_DIR}/<dependency>.
 #
 include(FetchContent)
-get_filename_component(PROJECT_ROOT_DIR "${CMAKE_CURRENT_SOURCE_DIR}" ABSOLUTE)
-file(MAKE_DIRECTORY "${FETCHCONTENT_BASE_DIR}")
-set(FETCHCONTENT_BASE_DIR "${PROJECT_ROOT_DIR}/.deps")
+file(MAKE_DIRECTORY ${FETCHCONTENT_BASE_DIR}) # Ensure the directory exists
 message(STATUS "FetchContent base directory: ${FETCHCONTENT_BASE_DIR}")
 
 #
@@ -252,7 +252,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
     message(STATUS "Building Marlin kernels for archs: ${MARLIN_ARCHS}")
   else()
     message(STATUS "Not building Marlin kernels as no compatible archs found"
-                   "in CUDA target architectures")
+                   " in CUDA target architectures")
   endif()
 
   #
@@ -432,7 +432,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
     message(STATUS "Building Marlin MOE kernels for archs: ${MARLIN_MOE_ARCHS}")
   else()
     message(STATUS "Not building Marlin MOE kernels as no compatible archs found"
-                   "in CUDA target architectures")
+                   " in CUDA target architectures")
   endif()
 endif()
 
@@ -509,6 +509,8 @@ else()
           GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
           GIT_TAG 013f0c4fc47e6574060879d9734c1df8c5c273bd
           GIT_PROGRESS TRUE
+          # Don't share the vllm-flash-attn build between build types
+          BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn
   )
 endif()
 

Dockerfile.openvino

@@ -15,11 +15,11 @@ RUN --mount=type=bind,source=.git,target=.git \
     if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
 
 # install build requirements
-RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/vllm/requirements-build.txt
+RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/requirements-build.txt
 # build vLLM with OpenVINO backend
-RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace/vllm/
+RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace
 
-COPY examples/ /workspace/vllm/examples
-COPY benchmarks/ /workspace/vllm/benchmarks
+COPY examples/ /workspace/examples
+COPY benchmarks/ /workspace/benchmarks
 
 CMD ["/bin/bash"]

Dockerfile.ppc64le

@@ -33,4 +33,4 @@ WORKDIR /workspace/
 
 RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
 
-ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
+ENTRYPOINT ["/opt/conda/bin/python3", "-m", "vllm.entrypoints.openai.api_server"]