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 10, 01:30 UTC
[CI] Update deepgemm to newer version (#32479)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Jan 16, 2026 at 12:18 UTC
9fd918e510c8981ccbab0380bf8d42fa81df1e9e
1 file changed
+1
-1
tools/install_deepgemm.sh
+1
-1
@@ -6,7 +6,7 @@ set -e
6
7
# Default values
8
DEEPGEMM_GIT_REPO="https://github.com/deepseek-ai/DeepGEMM.git"
9
-DEEPGEMM_GIT_REF="594953acce41793ae00a1233eb516044d604bcb6"
9
+DEEPGEMM_GIT_REF="0f5f2662027f0db05d4e3f6a94e56e2d8fc45c51"
10
WHEEL_DIR=""
11
12
# Parse command line arguments