xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 03:04:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Install pre-release version of apache-tvm-ffi for flashinfer (#27262)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor 2025-10-21 15:23:56 +01:00 committed by GitHub
parent 6c728f7771
commit bd66b8529b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docker/Dockerfile
View File

@ -132,7 +132,9 @@ WORKDIR /workspace
COPY requirements/common.txt requirements/common.txt COPY requirements/common.txt requirements/common.txt
COPY requirements/cuda.txt requirements/cuda.txt COPY requirements/cuda.txt requirements/cuda.txt
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --python /opt/venv/bin/python3 -r requirements/cuda.txt \ # TODO: remove apache-tvm-ffi once FlashInfer is fixed https://github.com/flashinfer-ai/flashinfer/issues/1962
uv pip install --python /opt/venv/bin/python3 --pre apache-tvm-ffi==0.1.0b15 \
&& uv pip install --python /opt/venv/bin/python3 -r requirements/cuda.txt \
--extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
# cuda arch list used by torch # cuda arch list used by torch
@ -353,7 +355,9 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# Install vllm wheel first, so that torch etc will be installed. # Install vllm wheel first, so that torch etc will be installed.
RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
--mount=type=cache,target=/root/.cache/uv \ --mount=type=cache,target=/root/.cache/uv \
uv pip install --system dist/*.whl --verbose \ # TODO: remove apache-tvm-ffi once FlashInfer is fixed https://github.com/flashinfer-ai/flashinfer/issues/1962
uv pip install --system --pre apache-tvm-ffi==0.1.0b15 \
&& uv pip install --system dist/*.whl --verbose \
--extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
# Install FlashInfer pre-compiled kernel cache and binaries # Install FlashInfer pre-compiled kernel cache and binaries