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