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 16, 15:45 UTC
[Bugfix] Avoid some bogus messages RE CUTLASS's revision when building (#8702)
Tyler Michael Smith committed
Sep 22, 2024 at 22:24 UTC
3dda7c22502033854e963fef3826c1f64627e33b
1 file changed
+4
CMakeLists.txt
+4
@@ -192,6 +192,10 @@ set(VLLM_EXT_SRC
192
193
if(VLLM_GPU_LANG STREQUAL "CUDA")
194
SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
195
+
196
+ # Set CUTLASS_REVISION manually -- its revision detection doesn't work in this case.
197
+ set(CUTLASS_REVISION "v3.5.1" CACHE STRING "CUTLASS revision to use")
198
+
199
FetchContent_Declare(
200
cutlass
201
GIT_REPOSITORY https://github.com/nvidia/cutlass.git