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
bump `flashinfer` to `v0.2.8` (#21385)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
cjackal committed
Jul 24, 2025 at 19:20 UTC
526078a96c52af678a1ddbdc3ecf78265e358f2b
1 file changed
+1
-1
docker/Dockerfile
+1
-1
@@ -390,7 +390,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
390
391
# Install FlashInfer from source
392
ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
393
-ARG FLASHINFER_GIT_REF="v0.2.8rc1"
393
+ARG FLASHINFER_GIT_REF="v0.2.8"
394
RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
395
. /etc/environment
396
git clone --depth 1 --recursive --shallow-submodules \