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, 05:30 UTC
[Bugfix] Bump DeepGEMM Version to Fix SMXX Layout Issues (#22606)
Signed-off-by: frankwang28 <frank.wbb@hotmail.com>
Frank Wang committed
Aug 12, 2025 at 15:43 UTC
ba81acbdc1eec643ba815a76628ae3e4b2263b76
1 file changed
+1
-1
docker/Dockerfile
+1
-1
@@ -432,7 +432,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
432
433
# Install DeepGEMM from source
434
ARG DEEPGEMM_GIT_REPO="https://github.com/deepseek-ai/DeepGEMM.git"
435
-ARG DEEPGEMM_GIT_REF="187656694f7f69e3e7975617a68bc3387680a7e1"
435
+ARG DEEPGEMM_GIT_REF="7b6b5563b9d4c1ae07ffbce7f78ad3ac9204827c"
436
RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
437
. /etc/environment
438
CUDA_MAJOR="${CUDA_VERSION%%.*}"