From 268a58e4e8d678645fb6df8b5b8ae0c308b83ff0 Mon Sep 17 00:00:00 2001 From: Taichang Zhou Date: Wed, 11 Feb 2026 21:18:53 +0800 Subject: [PATCH] Update pyproject.toml to remove redundant transformers package installation and adjust Dockerfile.ci to install the current package in editable mode. Also, update fa3-fwd package version in requirements/cuda.txt to 0.0.2 for consistency. Signed-off-by: Taichang Zhou --- docker/Dockerfile.ci | 5 +---- pyproject.toml | 3 +-- requirements/cuda.txt | 3 ++- 3 files changed, 4 insertions(+), 7 deletions(-) diff --git a/docker/Dockerfile.ci b/docker/Dockerfile.ci index 1f5fb28f6..daee9e923 100644 --- a/docker/Dockerfile.ci +++ b/docker/Dockerfile.ci @@ -20,9 +20,6 @@ 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 -# Pin nvidia-cublas-cu12 to a specific version -RUN uv pip install --system --upgrade --force-reinstall "nvidia-cublas-cu12==12.9.1.4" - # # 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. @@ -35,7 +32,7 @@ RUN uv pip install --system --upgrade --force-reinstall "nvidia-cublas-cu12==12. # flashinfer show-config # Install vllm-omni into the same uv-managed Python environment used by the base image. -RUN uv pip install --python "$(python3 -c 'import sys; print(sys.executable)')" --no-cache-dir ".[dev]" +RUN uv pip install --python "$(python3 -c 'import sys; print(sys.executable)')" --no-cache-dir -e . RUN ln -sf /usr/bin/python3 /usr/bin/python diff --git a/pyproject.toml b/pyproject.toml index 34a7c977e..6af193953 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -48,8 +48,7 @@ dev = [ "soundfile>=0.13.1", "imageio[ffmpeg]>=0.6.0", "opencv-python>=4.12.0.88", - "mooncake-transfer-engine==0.3.8.post1", - "transformers==4.57.6" + "mooncake-transfer-engine==0.3.8.post1" ] docs = [ diff --git a/requirements/cuda.txt b/requirements/cuda.txt index 823f47235..782b29e19 100644 --- a/requirements/cuda.txt +++ b/requirements/cuda.txt @@ -1,3 +1,4 @@ -r common.txt onnxruntime>=1.23.2 -fa3-fwd==0.0.1 +fa3-fwd==0.0.2 +nvidia-cublas-cu12==12.9.1.4