xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 12:19:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade FlashInfer to v0.3.0 (#24086)

Browse Source 
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
This commit is contained in:
Po-Han Huang (NVIDIA) 2025-09-05 00:49:20 +08:00 committed by GitHub
parent 94866d7c93
commit 78336a0c3e
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 # Install FlashInfer from source
ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git" ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
# Keep this in sync with "flashinfer" extra in setup.py # Keep this in sync with "flashinfer" extra in setup.py
ARG FLASHINFER_GIT_REF="v0.2.14.post1" ARG FLASHINFER_GIT_REF="v0.3.0"
# Flag to control whether to compile FlashInfer AOT kernels # Flag to control whether to compile FlashInfer AOT kernels
# Set to "true" to enable AOT compilation: # Set to "true" to enable AOT compilation:
# docker build --build-arg FLASHINFER_AOT_COMPILE=true ... # docker build --build-arg FLASHINFER_AOT_COMPILE=true ...

2
setup.py
View File

@ -694,7 +694,7 @@ setup(
"mistral_common[audio]"], # Required for audio processing "mistral_common[audio]"], # Required for audio processing
"video": [], # Kept for backwards compatibility "video": [], # Kept for backwards compatibility
# FlashInfer should be updated together with the Dockerfile # FlashInfer should be updated together with the Dockerfile
"flashinfer": ["flashinfer-python==0.2.14.post1"], "flashinfer": ["flashinfer-python==0.3.0"],
# Optional deps for AMD FP4 quantization support # Optional deps for AMD FP4 quantization support
"petit-kernel": ["petit-kernel"], "petit-kernel": ["petit-kernel"],
}, },