biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Bump Flashinfer Version and Re-enable DeepSeek NVFP4 AR+Norm Fusion (#34899)

Browse Source 
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Wei Zhao
2026-02-20 16:37:31 -05:00
committed by GitHub
parent 0632ed8778
commit ea5f903f80
5 changed files with 6 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docker/Dockerfile.nightly_torch
View File

@@ -217,13 +217,13 @@ RUN pip install setuptools==75.6.0 packaging==23.2 ninja==1.11.1.3 build==1.2.2.
# build flashinfer for torch nightly from source around 10 mins
# release version: v0.6.3
# release version: v0.6.4
# todo(elainewy): cache flashinfer build result for faster build
ENV CCACHE_DIR=/root/.cache/ccache
RUN --mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/root/.cache/uv \
echo "git clone flashinfer..." \
&& git clone --depth 1 --branch v0.6.3 --recursive https://github.com/flashinfer-ai/flashinfer.git \
&& git clone --depth 1 --branch v0.6.4 --recursive https://github.com/flashinfer-ai/flashinfer.git \
&& cd flashinfer \
&& git submodule update --init --recursive \
&& echo "finish git clone flashinfer..." \