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

Enhance configuration and debugging: Added asyncio mode to pytest settings, increased timeout for Qwen3-TTS E2E test, and improved logging in GPU model runner for better traceability of input modalities. Updated Dockerfile.ci to streamline VLLM installation process.

Browse Source 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-02-13 06:39:28 +00:00
1 parent 31e9fdbb57
commit 8a4eee9bed
5 files changed
+6 -16
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docker/Dockerfile.ci
+2 -13
View File
@@ -20,22 +20,11 @@ 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/2d5be1dd5ce2e44dfea53ea03ff61143da5137eb
# # 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
# Uninstall the old nvidia-cublas-cu12 brought by torch/vllm before reinstalling the pinned version
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 $(python3 -c ...) is expanded inside the container.
RUN /bin/bash -c 'VLLM_USE_PRECOMPILED=1 uv pip install --python "$(python3 -c "import sys; print(sys.executable)")" --no-cache-dir -e ".[dev]"'
RUN uv pip install --python "$(python3 -c 'import sys; print(sys.executable)')" --no-cache-dir ".[dev]"
RUN /bin/bash -c 'FLASHINFER_CUDA_TAG="$(python3 -c "import torch; print((torch.version.cuda or \"12.4\").replace(\".\", \"\"))")" && \
uv pip install --system --upgrade --force-reinstall \