Adaptiations to vllm-project#6484 and Merge remote-tracking branch 'github/main' into continous_batching_mamba_from_scratch

Author: mzusman

.buildkite/run-cpu-test-ppc64le.sh

@@ -18,7 +18,13 @@ docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/hugg
 # Run basic model test
 docker exec cpu-test bash -c "
   pip install pytest matplotlib einops transformers_stream_generator
-  pytest -v -s tests/models -m \"not vlm\" --ignore=tests/models/test_embedding.py --ignore=tests/models/test_oot_registration.py --ignore=tests/models/test_registry.py --ignore=tests/models/test_jamba.py --ignore=tests/models/test_danube3_4b.py" # Mamba and Danube3-4B on CPU is not supported
+  pytest -v -s tests/models -m \"not vlm\" \
+    --ignore=tests/models/test_embedding.py \
+    --ignore=tests/models/test_oot_registration.py \
+    --ignore=tests/models/test_registry.py \
+    --ignore=tests/models/test_jamba.py \
+    --ignore=tests/models/test_mamba.py \
+    --ignore=tests/models/test_danube3_4b.py" # Mamba kernels and Danube3-4B on CPU is not supported
 
 # online inference
 docker exec cpu-test bash -c "

.buildkite/run-cpu-test.sh

@@ -27,6 +27,7 @@ docker exec cpu-test bash -c "
   pytest -v -s tests/models/decoder_only/language \
     --ignore=tests/models/test_fp8.py \
     --ignore=tests/models/decoder_only/language/test_jamba.py \
+    --ignore=tests/models/decoder_only/language/test_mamba.py \
     --ignore=tests/models/decoder_only/language/test_granitemoe.py \
     --ignore=tests/models/decoder_only/language/test_danube3_4b.py" # Mamba and Danube3-4B on CPU is not supported
 

.buildkite/test-pipeline.yaml

@@ -121,7 +121,9 @@ steps:
   - vllm/core/
   - tests/distributed
   - tests/spec_decode/e2e/test_integration_dist_tp4
+  - tests/compile
   commands:
+  - pytest -v -s compile/test_basic_correctness.py
   - pytest -v -s distributed/test_pynccl.py
   - pytest -v -s spec_decode/e2e/test_integration_dist_tp4.py
 
@@ -231,14 +233,16 @@ steps:
   - vllm/
   - tests/compile
   commands:
-  - pytest -v -s compile/test_full_graph_smoke.py
+  - pytest -v -s compile/test_basic_correctness.py
 
-- label: "PyTorch Fullgraph Test" # 18min
-  source_file_dependencies:
-  - vllm/
-  - tests/compile
-  commands:
-  - pytest -v -s compile/test_full_graph.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: Kernels Test %N # 1h each
   mirror_hardwares: [amd]
@@ -343,10 +347,11 @@ steps:
     - pytest -v -s models/encoder_decoder/language
     - pytest -v -s models/encoder_decoder/vision_language
 
+# This test is used only in PR development phase to test individual models and should never run on main
 - label: Custom Models Test
-  #mirror_hardwares: [amd]
   optional: true
   commands:
+    - echo 'Testing custom models...'
     # PR authors can temporarily add commands below to test individual models
     # e.g. pytest -v -s models/encoder_decoder/vision_language/test_mllama.py
     # *To avoid merge conflicts, remember to REMOVE (not just comment out) them before merging the PR*
@@ -394,7 +399,7 @@ steps:
   - tests/distributed/
   - vllm/compilation
   commands:
-  - pytest -v -s ./compile/test_full_graph_multi_gpu.py
+  - 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

.github/CODEOWNERS

@@ -1,19 +1,30 @@
 # See https://help.github.com/articles/about-codeowners/
 # for more info about CODEOWNERS file
 
+# This lists cover the "core" components of vLLM that require careful review
+/vllm/attention/backends/abstract.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/core @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/engine/llm_engine.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/executor/executor_base.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/worker/worker_base.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/worker/worker.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/model_executor/layers/sampler.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+CMakeLists.txt @tlrmchlsmth @WoosukKwon
+
+# Test ownership
 /tests/async_engine @njhill @robertgshaw2-neuralmagic @simon-mo
 /tests/test_inputs.py @DarkLight1337 @ywang96
-/tests/entrypoints @DarkLight1337 @robertgshaw2-neuralmagic @simon-mo 
+/tests/entrypoints @DarkLight1337 @robertgshaw2-neuralmagic @simon-mo
 /tests/models @DarkLight1337 @ywang96
 /tests/multimodal @DarkLight1337 @ywang96
-/tests/prefix_caching @comaniac @KuntaiDu 
+/tests/prefix_caching @comaniac @KuntaiDu
 /tests/spec_decode @njhill @LiuXiaoxuanPKU
-/tests/kernels @tlrmchlsmth @WoosukKwon 
+/tests/kernels @tlrmchlsmth @WoosukKwon
 /tests/quantization @mgoin @robertgshaw2-neuralmagic
-/.buildkite/lm-eval-harness @mgoin @simon-mo 
+/.buildkite/lm-eval-harness @mgoin @simon-mo
 /tests/distributed/test_multi_node_assignment.py @youkaichao
 /tests/distributed/test_pipeline_parallel.py @youkaichao
 /tests/distributed/test_same_node.py @youkaichao
-/tests/multi_step @alexm-neuralmagic @SolitaryThinker @comaniac
+/tests/multi_step @alexm-neuralmagic @comaniac
 /tests/weight_loading @mgoin @youkaichao
 /tests/basic_correctness/test_chunked_prefill @rkooo567 @comaniac

.github/workflows/actionlint.yml

@@ -28,7 +28,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout"
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
+        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
         with:
           fetch-depth: 0
 

.github/workflows/add_label_automerge.yml

@@ -8,7 +8,7 @@ jobs:
         runs-on: ubuntu-latest
         steps:
             -   name: Add label
-                uses: actions/github-script@v6
+                uses: actions/github-script@v7
                 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@v3
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

.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@v3
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

.github/workflows/publish.yml

@@ -21,7 +21,7 @@ jobs:
       upload_url: ${{ steps.create_release.outputs.upload_url }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Extract branch info
         shell: bash
@@ -30,7 +30,7 @@ jobs:
 
       - name: Create Release
         id: create_release
-        uses: "actions/github-script@v6"
+        uses: "actions/github-script@v7"
         env:
           RELEASE_TAG: ${{ env.release_tag }}
         with:
@@ -54,7 +54,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup ccache
         uses: hendrikmuhs/ccache-action@v1.2
@@ -68,7 +68,7 @@ jobs:
           bash -x .github/workflows/scripts/env.sh
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
             python-version: ${{ matrix.python-version }}
 

.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@v6
+        uses: actions/github-script@v7
         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@v3
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

.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@v3
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

CMakeLists.txt

@@ -144,27 +144,32 @@ else()
 endif()
 
 
-#
-# For cuda we want to be able to control which architectures we compile for on 
-# a per-file basis in order to cut down on compile time. So here we extract
-# the set of architectures we want to compile for and remove the from the 
-# CMAKE_CUDA_FLAGS so that they are not applied globally.
-#
 if(VLLM_GPU_LANG STREQUAL "CUDA")
+  #
+  # For cuda we want to be able to control which architectures we compile for on 
+  # a per-file basis in order to cut down on compile time. So here we extract
+  # the set of architectures we want to compile for and remove the from the 
+  # CMAKE_CUDA_FLAGS so that they are not applied globally.
+  #
   clear_cuda_arches(CUDA_ARCH_FLAGS)
   extract_unique_cuda_archs_ascending(CUDA_ARCHS "${CUDA_ARCH_FLAGS}")
   message(STATUS "CUDA target architectures: ${CUDA_ARCHS}")
+  # Filter the target architectures by the supported supported archs
+  # since for some files we will build for all CUDA_ARCHS.
+  cuda_archs_loose_intersection(CUDA_ARCHS 
+    "${CUDA_SUPPORTED_ARCHS}" "${CUDA_ARCHS}")
+  message(STATUS "CUDA supported target architectures: ${CUDA_ARCHS}")
+else()
+  #
+  # For other GPU targets override the GPU architectures detected by cmake/torch
+  # and filter them by the supported versions for the current language.
+  # The final set of arches is stored in `VLLM_GPU_ARCHES`.
+  #
+  override_gpu_arches(VLLM_GPU_ARCHES
+    ${VLLM_GPU_LANG}
+    "${${VLLM_GPU_LANG}_SUPPORTED_ARCHS}")
 endif()
 
-#
-# Override the GPU architectures detected by cmake/torch and filter them by
-# the supported versions for the current language.
-# The final set of arches is stored in `VLLM_GPU_ARCHES`.
-#
-override_gpu_arches(VLLM_GPU_ARCHES
-  ${VLLM_GPU_LANG}
-  "${${VLLM_GPU_LANG}_SUPPORTED_ARCHS}")
-
 #
 # Query torch for additional GPU compilation flags for the given
 # `VLLM_GPU_LANG`.

Dockerfile.cpu

@@ -26,7 +26,8 @@ RUN pip install intel_extension_for_pytorch==2.4.0
 
 WORKDIR /workspace
 
-ENV PIP_EXTRA_INDEX_URL=https://download.pytorch.org/whl/cpu
+ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
+ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
 RUN --mount=type=cache,target=/root/.cache/pip \
     --mount=type=bind,src=requirements-build.txt,target=requirements-build.txt \
     pip install --upgrade pip && \

benchmarks/benchmark_serving.py

@@ -176,9 +176,9 @@ def sample_sonnet_requests(
     # Sample the rest of lines per request.
     sampled_requests: List[Tuple[str, int, int]] = []
     for _ in range(num_requests):
-        sampled_lines = "".join(
-            prefix_lines +
-            random.sample(poem_lines, num_input_lines - num_prefix_lines))
+        num_lines_needed = num_input_lines - num_prefix_lines
+        sampled_lines = "".join(prefix_lines +
+                                random.choices(poem_lines, k=num_lines_needed))
 
         prompt = f"{base_prompt}{sampled_lines}"
         message = [
@@ -536,7 +536,7 @@ def process_one_metric(
         # E.g., "Time to First Token"
         metric_header: str,
     ):
-        # This function print and add statistics of the specified
+        # This function prints and adds statistics of the specified
         # metric.
         if metric_attribute_name not in selected_percentile_metrics:
             return

csrc/quantization/machete/machete_pytorch.cu

@@ -89,6 +89,10 @@ torch::Tensor prepack_B(torch::Tensor const& B,
 TORCH_LIBRARY_IMPL_EXPAND(TORCH_EXTENSION_NAME, CUDA, m) {
   m.impl("machete_prepack_B", &prepack_B);
   m.impl("machete_gemm", &gemm);
+}
+
+// use CatchAll since supported_schedules has no tensor arguments
+TORCH_LIBRARY_IMPL(TORCH_EXTENSION_NAME, CatchAll, m) {
   m.impl("machete_supported_schedules", &supported_schedules);
 }