fix conflict

vllm-project · Oct 19, 2024 · 1690e82 · 1690e82
2 parents 9cd16bc + 8e3e7f2
commit 1690e82
Show file tree

Hide file tree

Showing 287 changed files with 9,933 additions and 5,757 deletions.
diff --git a/.buildkite/release-pipeline.yaml b/.buildkite/release-pipeline.yaml
@@ -3,7 +3,7 @@ steps:
     agents:
       queue: cpu_queue
     commands:
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg buildkite_commit=$BUILDKITE_COMMIT --build-arg USE_SCCACHE=1 --build-arg CUDA_VERSION=12.1.0 --tag vllm-ci:build-image --target build --progress plain ."
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.1.0 --tag vllm-ci:build-image --target build --progress plain ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
       # rename the files to change linux -> manylinux1
@@ -22,7 +22,7 @@ steps:
     agents:
       queue: cpu_queue
     commands:
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg buildkite_commit=$BUILDKITE_COMMIT --build-arg USE_SCCACHE=1 --build-arg CUDA_VERSION=11.8.0 --tag vllm-ci:build-image --target build --progress plain ."
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=11.8.0 --tag vllm-ci:build-image --target build --progress plain ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
       # rename the files to change linux -> manylinux1

diff --git a/.buildkite/run-cpu-test.sh b/.buildkite/run-cpu-test.sh
@@ -32,10 +32,10 @@ docker exec cpu-test bash -c "
     --ignore=tests/models/decoder_only/language/test_danube3_4b.py" # Mamba and Danube3-4B on CPU is not supported
 
 # Run compressed-tensor test
-# docker exec cpu-test bash -c "
-#   pytest -s -v \
-#   tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_static_setup \
-#   tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynanmic_per_token"
+docker exec cpu-test bash -c "
+  pytest -s -v \
+  tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_static_setup \
+  tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token"
 
 # Run AWQ test
 docker exec cpu-test bash -c "

diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml
@@ -77,8 +77,8 @@ steps:
   - vllm/
   - tests/basic_correctness/test_chunked_prefill
   commands:
-  - VLLM_ATTENTION_BACKEND=XFORMERS VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1 pytest -v -s basic_correctness/test_chunked_prefill.py
-  - VLLM_ATTENTION_BACKEND=FLASH_ATTN VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1 pytest -v -s basic_correctness/test_chunked_prefill.py
+  - VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_chunked_prefill.py
+  - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py
 
 - label: Core Test # 10min
   mirror_hardwares: [amd]
@@ -88,11 +88,7 @@ steps:
   - vllm/distributed
   - tests/core
   commands:
-  - VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1  pytest -v -s core/test_scheduler.py
-  - VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1  pytest -v -s core core/test_chunked_prefill_scheduler.py
-  - VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1  pytest -v -s core core/block/e2e/test_correctness.py
-  - VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1  pytest -v -s core core/block/e2e/test_correctness_sliding_window.py
-  - pytest -v -s core --ignore=core/block/e2e/test_correctness.py --ignore=core/test_scheduler.py --ignore=core/test_chunked_prefill_scheduler.py --ignore=core/block/e2e/test_correctness.py --ignore=core/block/e2e/test_correctness_sliding_window.py
+  - pytest -v -s core
 
 - label: Entrypoints Test # 40min
   working_dir: "/vllm-workspace/tests"
@@ -184,15 +180,15 @@ steps:
     - python3 offline_inference_vision_language_multi_image.py
     - python3 tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors
     - python3 offline_inference_encoder_decoder.py
+    - python3 offline_profile.py --model facebook/opt-125m
 
 - label: Prefix Caching Test # 9min
   #mirror_hardwares: [amd]
   source_file_dependencies:
   - vllm/
   - tests/prefix_caching
   commands:
-    - VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1 pytest -v -s prefix_caching/test_prefix_caching.py
-    - pytest -v -s prefix_caching --ignore=prefix_caching/test_prefix_caching.py
+    - pytest -v -s prefix_caching
 
 - label: Samplers Test # 36min
   source_file_dependencies:
@@ -216,8 +212,7 @@ steps:
   - tests/spec_decode
   commands:
     - pytest -v -s spec_decode/e2e/test_multistep_correctness.py
-    - VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1 pytest -v -s spec_decode/e2e/test_compatibility.py
-    - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s spec_decode --ignore=spec_decode/e2e/test_multistep_correctness.py --ignore=spec_decode/e2e/test_compatibility.py
+    - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s spec_decode --ignore=spec_decode/e2e/test_multistep_correctness.py
 
 - label: LoRA Test %N # 15min each
   mirror_hardwares: [amd]
@@ -235,14 +230,12 @@ steps:
   commands:
   - pytest -v -s compile/test_basic_correctness.py
 
-# TODO: re-write in comparison tests, and fix symbolic shape
-# for quantization ops.
-# - label: "PyTorch Fullgraph Test" # 18min
-#   source_file_dependencies:
-#   - vllm/
-#   - tests/compile
-#   commands:
-#   - pytest -v -s compile/test_full_graph.py
+- label: "PyTorch Fullgraph Test" # 18min
+  source_file_dependencies:
+  - vllm/
+  - tests/compile
+  commands:
+  - pytest -v -s compile/test_full_graph.py
 
 - label: Kernels Test %N # 1h each
   mirror_hardwares: [amd]
@@ -340,10 +333,12 @@ steps:
   source_file_dependencies:
   - vllm/
   - tests/models/embedding/language
+  - tests/models/embedding/vision_language
   - tests/models/encoder_decoder/language
   - tests/models/encoder_decoder/vision_language
   commands:
     - pytest -v -s models/embedding/language
+    - pytest -v -s models/embedding/vision_language
     - pytest -v -s models/encoder_decoder/language
     - pytest -v -s models/encoder_decoder/vision_language
 
@@ -402,7 +397,7 @@ steps:
   - pytest -v -s ./compile/test_basic_correctness.py
   - pytest -v -s ./compile/test_wrapper.py
   - VLLM_TEST_SAME_HOST=1 torchrun --nproc-per-node=4 distributed/test_same_node.py | grep -q 'Same node test passed'
-  - TARGET_TEST_SUITE=L4 VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1=1  pytest basic_correctness/ -v -s -m distributed_2_gpus
+  - TARGET_TEST_SUITE=L4 pytest basic_correctness/ -v -s -m distributed_2_gpus
   # Avoid importing model tests that cause CUDA reinitialization error
   - pytest models/encoder_decoder/language/test_bart.py -v -s -m distributed_2_gpus
   - pytest models/encoder_decoder/vision_language/test_broadcast.py -v -s -m distributed_2_gpus

diff --git a/.dockerignore b/.dockerignore
@@ -1,6 +1,33 @@
-/.github/
 /.venv
 /build
 dist
-Dockerfile*
 vllm/*.so
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+.mypy_cache
+
+# Distribution / packaging
+.Python
+/build/
+cmake-build-*/
+CMakeUserPresets.json
+develop-eggs/
+/dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
diff --git a/.github/workflows/actionlint.yml b/.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
diff --git a/.github/workflows/add_label_automerge.yml b/.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({

diff --git a/.github/workflows/clang-format.yml b/.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" "${EXCLUDES[@]}") \
-            | xargs clang-format --dry-run --Werror
+            | xargs clang-format --dry-run --Werror
diff --git a/.github/workflows/matchers/mypy.json b/.github/workflows/matchers/mypy.json
@@ -0,0 +1,16 @@
+{
+  "problemMatcher": [
+    {
+      "owner": "mypy",
+      "pattern": [
+        {
+          "regexp": "^(.+):(\\d+):\\s(error|warning):\\s(.+)$",
+          "file": 1,
+          "line": 2,
+          "severity": 3,
+          "message": 4
+        }
+      ]
+    }
+  ]
+}
diff --git a/.github/workflows/matchers/ruff.json b/.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
+          }
+        ]
+      }
+    ]
+  }
diff --git a/.github/workflows/mypy.yaml b/.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
diff --git a/.github/workflows/publish.yml b/.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:

diff --git a/.github/workflows/reminder_comment.yml b/.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({

diff --git a/.github/workflows/ruff.yml b/.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

diff --git a/.github/workflows/scripts/build.sh b/.github/workflows/scripts/build.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+set -eux
 
 python_executable=python$1
 cuda_home=/usr/local/cuda-$2
@@ -8,13 +9,15 @@ PATH=${cuda_home}/bin:$PATH
 LD_LIBRARY_PATH=${cuda_home}/lib64:$LD_LIBRARY_PATH
 
 # Install requirements
-$python_executable -m pip install wheel packaging 'setuptools-scm>=8'
-$python_executable -m pip install -r requirements-cuda.txt
+$python_executable -m pip install -r requirements-build.txt -r requirements-cuda.txt
 
 # Limit the number of parallel jobs to avoid OOM
 export MAX_JOBS=1
 # Make sure release wheels are built for the following architectures
 export TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX"
 export VLLM_FA_CMAKE_GPU_ARCHES="80-real;90-real"
+
+bash tools/check_repo.sh
+
 # Build
 $python_executable setup.py bdist_wheel --dist-dir=dist
diff --git a/.github/workflows/yapf.yml b/.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

diff --git a/.readthedocs.yaml b/.readthedocs.yaml
@@ -13,10 +13,10 @@ sphinx:
    fail_on_warning: true
 
 # If using Sphinx, optionally build your docs in additional formats such as PDF
-formats:
-   - pdf
+formats: []
 
 # Optionally declare the Python requirements required to build your docs
 python:
    install:
    - requirements: docs/requirements-docs.txt
+