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 12, 21:00 UTC
[Misc] don't cache `CUTLASS_REVISION` var in CMakeLists.txt (#28518)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com> Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Jinzhen Lin committed
Nov 20, 2025 at 18:52 UTC
edfe867208482ccadbf0ef503fc43e1fbb1e48f6
1 file changed
+1
-1
CMakeLists.txt
+1
-1
@@ -307,7 +307,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
307
SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
308
309
# Set CUTLASS_REVISION. Used for FetchContent. Also fixes some bogus messages when building.
310
- set(CUTLASS_REVISION "v4.2.1" CACHE STRING "CUTLASS revision to use")
310
+ set(CUTLASS_REVISION "v4.2.1")
311
312
# Use the specified CUTLASS source directory for compilation if VLLM_CUTLASS_SRC_DIR is provided
313
if (DEFINED ENV{VLLM_CUTLASS_SRC_DIR})