biondizzle/grace-gpu-containers
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update flashinfer to v0.6.6 to match vLLM 0.18.x requirements

Browse Source 
vLLM 0.18.x depends on flashinfer-python==0.6.6, was building 0.4.1
This commit is contained in:
biondizzle
2026-04-03 07:13:16 +00:00
parent 9d88d4c7d8
commit ceab7ada22
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/Dockerfile
View File

@@ -80,7 +80,7 @@ RUN mkdir -p /wheels && \
FROM build-base AS build-flashinfer FROM build-base AS build-flashinfer
ARG FLASHINFER_ENABLE_AOT=1 ARG FLASHINFER_ENABLE_AOT=1
ARG FLASHINFER_REF=v0.4.1 ARG FLASHINFER_REF=v0.6.6
ARG FLASHINFER_BUILD_SUFFIX=cu130 ARG FLASHINFER_BUILD_SUFFIX=cu130
ENV FLASHINFER_LOCAL_VERSION=${FLASHINFER_BUILD_SUFFIX:-} ENV FLASHINFER_LOCAL_VERSION=${FLASHINFER_BUILD_SUFFIX:-}
RUN git clone https://github.com/flashinfer-ai/flashinfer.git RUN git clone https://github.com/flashinfer-ai/flashinfer.git