@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 3dda7c2250
Fork 0

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