anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Enhance Dockerfile.ci by adding a debug step to print key dependency versions for CI troubleshooting, while commenting out the flashinfer version sync logic for clarity.

Browse Source 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-02-11 06:01:01 +00:00
1 parent 31b6584373
commit 379f61d038
1 file changed
+19 -10
Download Patch File Download Diff File Expand all files Collapse all files
docker/Dockerfile.ci
+19 -10
View File
@@ -20,20 +20,29 @@ RUN apt-get update && \
# 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/4a1550d22d7058e129d0e1257e726b3bf4a77025
# Keep flashinfer runtime packages in version sync.
# We derive the version from installed flashinfer (pulled by vllm)
# and enforce the same version for flashinfer-cubin / flashinfer-jit-cache.
RUN FLASHINFER_VERSION="$(python3 -c 'import importlib.metadata as m; print(m.version("flashinfer-python"))' 2>/dev/null || python3 -c 'import importlib.metadata as m; print(m.version("flashinfer"))')" && \
FLASHINFER_CUDA_TAG="$(python3 -c 'import torch; print((torch.version.cuda or "12.4").replace(".", ""))')" && \
uv pip install --system --upgrade --force-reinstall \
"flashinfer-cubin==${FLASHINFER_VERSION}" \
"flashinfer-jit-cache==${FLASHINFER_VERSION}" \
--extra-index-url "https://flashinfer.ai/whl/cu${FLASHINFER_CUDA_TAG}" && \
flashinfer show-config
# # Keep flashinfer runtime packages in version sync.
# # We derive the version from installed flashinfer (pulled by vllm)
# # and enforce the same version for flashinfer-cubin / flashinfer-jit-cache.
# RUN FLASHINFER_VERSION="$(python3 -c 'import importlib.metadata as m; print(m.version("flashinfer-python"))' 2>/dev/null || python3 -c 'import importlib.metadata as m; print(m.version("flashinfer"))')" && \
# FLASHINFER_CUDA_TAG="$(python3 -c 'import torch; print((torch.version.cuda or "12.4").replace(".", ""))')" && \
# uv pip install --system --upgrade --force-reinstall \
# "flashinfer-cubin==${FLASHINFER_VERSION}" \
# "flashinfer-jit-cache==${FLASHINFER_VERSION}" \
# --extra-index-url "https://flashinfer.ai/whl/cu${FLASHINFER_CUDA_TAG}" && \
# flashinfer show-config
# Install vllm-omni into the same uv-managed Python environment used by the base image.
RUN uv pip install --python "$(python3 -c 'import sys; print(sys.executable)')" --no-cache-dir ".[dev]"
# Debug: print key dependency versions for CI troubleshooting
RUN python3 -c "\
import transformers, torch, vllm; \
print(f'transformers={transformers.__version__}'); \
print(f'torch={torch.__version__}'); \
print(f'vllm={vllm.__version__}'); \
print(f'cuda={torch.version.cuda}'); \
"
RUN ln -sf /usr/bin/python3 /usr/bin/python
ENTRYPOINT []