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 14, 23:45 UTC
update flashinfer to v0.2.9rc2 (#21701)
Signed-off-by: Weiliang Liu <weiliangl@nvidia.com>
weiliang committed
Jul 29, 2025 at 03:31 UTC
01c753ed98c798a8545f038df86424c0dabe3ac8
1 file changed
+1
-1
docker/Dockerfile
+1
-1
@@ -386,7 +386,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
386
387
# Install FlashInfer from source
388
ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
389
-ARG FLASHINFER_GIT_REF="v0.2.9rc1"
389
+ARG FLASHINFER_GIT_REF="v0.2.9rc2"
390
RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
391
. /etc/environment
392
git clone --depth 1 --recursive --shallow-submodules \