Merge origin/main into dev/vllm-align

Resolve conflicts:
- docker/Dockerfile.ci: Keep wheel install section, update hash to 6042e66cd5
- vllm_omni/platforms/npu/worker/npu_model_runner.py: Accept main's refactoring

Made-with: Cursor

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

docker/Dockerfile.ci

@@ -1,5 +1,5 @@
 ARG VLLM_BASE_IMAGE=vllm/vllm-openai
-ARG VLLM_BASE_TAG=v0.15.0
+ARG VLLM_BASE_TAG=v0.16.0
 FROM ${VLLM_BASE_IMAGE}:${VLLM_BASE_TAG}
 ARG APP_DIR=/workspace/vllm-omni
 WORKDIR ${APP_DIR}
@@ -8,38 +8,23 @@ COPY . .
 
 # Install system dependencies
 RUN apt-get update && \
-    apt-get install -y ffmpeg sox libsox-fmt-all && \
+    apt-get install -y ffmpeg sox libsox-fmt-all jq && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
 # Install vLLM wheel for the specific commit
 # URL format: https://wheels.vllm.ai/<commit_hash>/
-# Current vLLM wheel commit: 24650715105a26b41c88f4164777b5e1a0f3200b
+# Current vLLM wheel commit: 6042e66cd5304fc043d96aaa0c22d56f939af320
 # Note: --prerelease=allow is required because nightly/commit wheels use
 # pre-release version numbers (e.g. 2.10.0.dev...) which uv ignores by default,
 # causing it to fall back to the older stable release from PyPI.
-RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/24650715105a26b41c88f4164777b5e1a0f3200b
-
+RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/6042e66cd5304fc043d96aaa0c22d56f939af320
 
 RUN uv pip uninstall --system nvidia-cublas-cu12
 # Install vllm-omni into the same uv-managed Python environment used by the base image.
 # Use bash -c so that $(python3 -c ...) is expanded inside the container.
 RUN uv pip install --system --no-cache-dir ".[dev]"
 
-# pplx_kernels is optional; the base image may already ship a version.
-# Reinstall attempt may fail if no compatible wheel exists for the current
-# PyTorch/CUDA combination – allow the build to continue regardless.
-RUN pip install --upgrade --force-reinstall "pplx_kernels" || true
-
-RUN /bin/bash -c 'FLASHINFER_CUDA_TAG="$(python3 -c "import torch; print((torch.version.cuda or \"12.4\").replace(\".\", \"\"))")" && \
-    uv pip install --system --upgrade --force-reinstall \
-      "flashinfer-python==0.6.3" \
-      "flashinfer-cubin==0.6.3" \
-      "flashinfer-jit-cache==0.6.3" \
-      --extra-index-url "https://flashinfer.ai/whl/cu${FLASHINFER_CUDA_TAG}"'
-# Pin nvidia-cublas-cu12 after vllm-omni install so dependency resolution does not overwrite it
-RUN uv pip install --system --upgrade --force-reinstall "nvidia-cublas-cu12==12.9.1.4"
-RUN uv pip install --system --upgrade --force-reinstall "numpy==2.2.6"
 RUN ln -sf /usr/bin/python3 /usr/bin/python
 
 ENTRYPOINT []

docker/Dockerfile.npu

@@ -7,8 +7,9 @@ WORKDIR ${APP_DIR}
 
 COPY . .
 
-# Install vllm-omni with dev dependencies
-RUN pip install --no-cache-dir -e . --no-build-isolation
+RUN sed -i -E 's/^([[:space:]]*)"fa3-fwd==0\.0\.1",/\1# "fa3-fwd==0.0.1",/' pyproject.toml \
+ && sed -i -E 's/\bonnxruntime\b/onnxruntime-cann/g' pyproject.toml
+RUN pip install -v -e .
 
 ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
 

docker/Dockerfile.npu.a3

@@ -7,8 +7,9 @@ WORKDIR ${APP_DIR}
 
 COPY . .
 
-# Install vllm-omni with dev dependencies
-RUN pip install --no-cache-dir -e . --no-build-isolation
+RUN sed -i -E 's/^([[:space:]]*)"fa3-fwd==0\.0\.1",/\1# "fa3-fwd==0.0.1",/' pyproject.toml \
+ && sed -i -E 's/\bonnxruntime\b/onnxruntime-cann/g' pyproject.toml
+RUN pip install -v -e .
 
 ENV VLLM_WORKER_MULTIPROC_METHOD=spawn