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 15, 12:15 UTC
[Build/CI] Upgrade CUTLASS to 3.9.2 (#17641)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Tyler Michael Smith committed
May 4, 2025 at 22:23 UTC
f62cad6431e2bce91c033c74e20835c8e0c9b288
1 file changed
+1
-1
CMakeLists.txt
+1
-1
@@ -250,7 +250,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
250
SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
251
252
# Set CUTLASS_REVISION. Used for FetchContent. Also fixes some bogus messages when building.
253
- set(CUTLASS_REVISION "v3.9.1" CACHE STRING "CUTLASS revision to use")
253
+ set(CUTLASS_REVISION "v3.9.2" CACHE STRING "CUTLASS revision to use")
254
255
# Use the specified CUTLASS source directory for compilation if VLLM_CUTLASS_SRC_DIR is provided
256
if (DEFINED ENV{VLLM_CUTLASS_SRC_DIR})