xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-25 05:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Bump Flashinfer to 0.3.1 (#24868)

Browse Source 
Signed-off-by: bbartels <benjamin@bartels.dev>
This commit is contained in:
Benjamin Bartels 2025-09-15 20:45:55 +01:00 committed by GitHub
parent 49bfc538e4
commit 94b03f88dd
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

@ -375,7 +375,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
# Install FlashInfer from source
ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
# Keep this in sync with "flashinfer" extra in setup.py
ARG FLASHINFER_GIT_REF="v0.3.0"
ARG FLASHINFER_GIT_REF="v0.3.1"
# Flag to control whether to compile FlashInfer AOT kernels
# Set to "true" to enable AOT compilation:
# docker build --build-arg FLASHINFER_AOT_COMPILE=true ...

2
setup.py
View File

@ -664,7 +664,7 @@ setup(
"mistral_common[audio]"], # Required for audio processing
"video": [], # Kept for backwards compatibility
# FlashInfer should be updated together with the Dockerfile
"flashinfer": ["flashinfer-python==0.3.0"],
"flashinfer": ["flashinfer-python==0.3.1"],
# Optional deps for AMD FP4 quantization support
"petit-kernel": ["petit-kernel"],
},