A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 2, 03:30 UTC
[docker] Stop using extra-index-url for flashinfer-jit-cache (#44366)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Kevin H. Luu committed
Jun 2, 2026 at 18:58 UTC
27a93cd4266151beaf7c8a89227418e86e187f30
1 file changed
+1
-1
docker/Dockerfile
+1
-1
@@ -760,7 +760,7 @@ RUN --mount=type=cache,target=/opt/uv/cache \
760
ARG FLASHINFER_VERSION=0.6.12
761
RUN --mount=type=cache,target=/opt/uv/cache \
762
uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} \
763
- --extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
763
+ --index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
764
765
# ============================================================
766
# OPENAI API SERVER DEPENDENCIES