tzhouam
473d3ecd29
- Updated the vLLM wheel commit hash in Dockerfile.ci to a60985b07eaf0fefa4c353ad2309b745707591ed. - Modified the mock shared memory handle name in test_basic_connectors.py for clarity. - Increased GPU memory utilization to 0.9 and adjusted max_num_batched_tokens to 4096 in qwen2_5_omni_ci.yaml to enable testing on H800. - Refactored GPU model runner classes to remove deprecated activate_lora parameter and ensure compatibility with num_active_loras. - Enhanced request handling in the OmniGPUModelRunner class to improve streaming request updates. Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
31 lines
1.2 KiB
Docker
31 lines
1.2 KiB
Docker
ARG VLLM_BASE_IMAGE=vllm/vllm-openai
|
|
ARG VLLM_BASE_TAG=v0.16.0
|
|
FROM ${VLLM_BASE_IMAGE}:${VLLM_BASE_TAG}
|
|
ARG APP_DIR=/workspace/vllm-omni
|
|
WORKDIR ${APP_DIR}
|
|
|
|
COPY . .
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && \
|
|
apt-get install -y ffmpeg git 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: a60985b07eaf0fefa4c353ad2309b745707591ed
|
|
# 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/a60985b07eaf0fefa4c353ad2309b745707591ed
|
|
|
|
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]"
|
|
|
|
RUN ln -sf /usr/bin/python3 /usr/bin/python
|
|
|
|
ENTRYPOINT []
|