xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 03:15:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade FlashInfer to v0.2.11 (#22613)

Browse Source 
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Po-Han Huang (NVIDIA) 2025-08-12 10:58:41 +08:00 committed by GitHub
parent 839ab00349
commit dc5e4a653c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docker/Dockerfile
View File

@ -387,7 +387,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
# Keep this in sync with https://github.com/vllm-project/vllm/blob/main/requirements/cuda.txt
# We use `--force-reinstall --no-deps` to avoid issues with the existing FlashInfer wheel.
ARG FLASHINFER_GIT_REF="v0.2.10"
ARG FLASHINFER_GIT_REF="v0.2.11"
RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
. /etc/environment
git clone --depth 1 --recursive --shallow-submodules \

2
setup.py
View File

@ -684,7 +684,7 @@ setup(
"mistral_common[audio]"], # Required for audio processing
"video": [], # Kept for backwards compatibility
# FlashInfer should be updated together with the Dockerfile
"flashinfer": ["flashinfer-python==0.2.10"],
"flashinfer": ["flashinfer-python==0.2.11"],
},
cmdclass=cmdclass,
package_data=package_data,