Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
37 lines
1.2 KiB
Docker
37 lines
1.2 KiB
Docker
ARG NIGHTLY_DATE="20250730"
|
|
ARG BASE_IMAGE="us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/xla:nightly_3.12_tpuvm_$NIGHTLY_DATE"
|
|
|
|
FROM $BASE_IMAGE
|
|
WORKDIR /workspace/vllm
|
|
|
|
# Install some basic utilities
|
|
RUN apt-get update && apt-get install -y \
|
|
git \
|
|
ffmpeg libsm6 libxext6 libgl1 && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
# Build vLLM.
|
|
COPY . .
|
|
ARG GIT_REPO_CHECK=0
|
|
RUN --mount=type=bind,source=.git,target=.git \
|
|
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh; fi
|
|
|
|
# Remove existing versions of dependencies
|
|
# TODO: These packages will remain as dead weight in the Docker image layers.
|
|
# We should find a way to build the image without uninstalling these.
|
|
# Consider using a different base image.
|
|
RUN pip uninstall -y torch torch_xla torchvision
|
|
|
|
ENV VLLM_TARGET_DEVICE="tpu"
|
|
RUN --mount=type=cache,target=/root/.cache/pip \
|
|
--mount=type=bind,source=.git,target=.git \
|
|
python3 -m pip install \
|
|
-r requirements/tpu.txt
|
|
|
|
RUN --mount=type=cache,target=/root/.cache/pip python3 -m pip install -e .
|
|
|
|
# install development dependencies (for testing)
|
|
RUN --mount=type=cache,target=/root/.cache/pip python3 -m pip install -e tests/vllm_test_utils
|
|
|
|
CMD ["/bin/bash"]
|