@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 6a11fdfbb8
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, 19:30 UTC

[CI/Build][Bugfix] Fix CUTLASS header-only line (#7034)

Tyler Michael Smith committed Aug 1, 2024 at 16:51 UTC 6a11fdfbb8d6701c7ad38648aead23d8cbe6aac5
1 file changed +4 -1
CMakeLists.txt
+4 -1
@@ -156,12 +156,15 @@ set(VLLM_EXT_SRC
156
157 if(VLLM_GPU_LANG STREQUAL "CUDA")
158 include(FetchContent)
159 - SET(CUTLASS_ENABLE_HEADERS_ONLY=ON)
159 + SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
160 FetchContent_Declare(
161 cutlass
162 GIT_REPOSITORY https://github.com/nvidia/cutlass.git
163 # CUTLASS 3.5.0
164 GIT_TAG 7d49e6c7e2f8896c47f586706e67e1fb215529dc
165 + # Shallow clone with depth 1
166 + GIT_SHALLOW TRUE
167 + GIT_PROGRESS TRUE
168 )
169 FetchContent_MakeAvailable(cutlass)
170