63 lines
2.6 KiB
Docker
63 lines
2.6 KiB
Docker
# Target vllm version: v0.24.0 (releases/v0.24.0 branch).
|
|
# The pinned VLLM_PRECOMPILED_WHEEL_COMMIT and VLLM_BASE_TAG below must
|
|
# be updated on every rebase to match the new upstream vllm commit/tag.
|
|
ARG VLLM_BASE_IMAGE=vllm/vllm-openai
|
|
ARG VLLM_BASE_TAG=v0.24.0
|
|
FROM ${VLLM_BASE_IMAGE}:${VLLM_BASE_TAG}
|
|
ARG APP_DIR=/workspace/vllm-omni
|
|
WORKDIR ${APP_DIR}
|
|
COPY . .
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && \
|
|
apt-get install -y espeak-ng git jq && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
|
|
# Install vLLM (CUDA 13.0 build) from precompiled wheel at the selected commit.
|
|
# Must use direct URL because the wheel has a PEP 440 local version identifier
|
|
# (e.g. +gaeee7ef93.cu130) which pip/uv refuse to install from a PEP 503 package index.
|
|
# The cu130 wheel index lives at /<commit>/cu130/vllm/ but the actual wheel files
|
|
# are stored at the top level /<commit>/<wheel>.
|
|
ENV VLLM_PRECOMPILED_WHEEL_COMMIT=2dfaae752b4db0d43cfc0715c780e33be030d0f1
|
|
# Ensure CUDA library path is in LD_LIBRARY_PATH so bitsandbytes' precompiled
|
|
# C extension can find libnvJitLink.so.13 (CUDA 13.x JIT linker) at import time.
|
|
# The base vLLM image has bitsandbytes pre-installed; without this env var,
|
|
# worker subprocesses fail to load bitsandbytes' C extension, producing
|
|
# OSError tracebacks that pollute CI logs.
|
|
ENV LD_LIBRARY_PATH=/usr/local/cuda/targets/x86_64-linux/lib:${LD_LIBRARY_PATH}
|
|
RUN VLLM_WHEEL_URL=$(python3 -c "import urllib.request,re; \
|
|
from urllib.parse import urljoin, quote; \
|
|
index_url='https://wheels.vllm.ai/${VLLM_PRECOMPILED_WHEEL_COMMIT}/cu130/vllm/'; \
|
|
html=urllib.request.urlopen(index_url).read().decode(); \
|
|
m=re.search(r'href=\"([^\"]*x86_64\.whl)\"',html); \
|
|
assert m, f'No x86_64 vLLM wheel found at {index_url}'; \
|
|
print(quote(urljoin(index_url,m.group(1)), safe=':/+%'))") && \
|
|
echo "Installing vLLM from: ${VLLM_WHEEL_URL}" && \
|
|
uv pip install --system --force-reinstall "${VLLM_WHEEL_URL}"
|
|
|
|
|
|
|
|
RUN uv pip install --system ".[dev]"
|
|
|
|
RUN uv pip install --system --upgrade \
|
|
"flashinfer-python==0.6.13" \
|
|
"flashinfer-cubin==0.6.13" \
|
|
"numpy==2.2.6"
|
|
|
|
RUN uv pip install --system --upgrade \
|
|
"flashinfer-jit-cache==0.6.13" \
|
|
--index-url https://flashinfer.ai/whl/cu130
|
|
|
|
# Force-reinstall torch AFTER flashinfer, because flashinfer --upgrade pulls in
|
|
# a newer torch (2.12.x) whose libtorch_cuda.so lacks
|
|
# at::cuda::getCurrentCUDABlasHandle, causing "undefined symbol" at import time.
|
|
RUN uv pip install --system --force-reinstall \
|
|
"torch==2.11.0" "torchaudio==2.11.0" "torchvision==0.26.0" \
|
|
--torch-backend cu130
|
|
|
|
RUN ln -sf /usr/bin/python3 /usr/bin/python
|
|
|
|
ENTRYPOINT []
|