hailin
/
sglang_v0.5.2
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

.

This commit is contained in:
hailin 2025-09-18 09:11:23 +08:00
parent 8be830f035
commit fe05117825
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@ -77,7 +77,7 @@ WORKDIR /opt/flashinfer
ENV FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.6 8.9 9.0a"
# 先做 AOT 预编译，再直接打 wheel（不隔离，使用同一份自编 torch）
RUN python3 -m pip install --no-cache-dir numpy requests build "cuda-python>=12.0,<13" "nvidia-nvshmem-cu12" pynvml && \
RUN python3 -m pip install --no-cache-dir numpy requests build "cuda-python>=12.0,<13" "nvidia-nvshmem-cu12" ninja pynvml && \
python3 -m flashinfer.aot && \
python3 -m build --no-isolation --wheel && \
ls -lh dist/