[Kernel] Porting the TRTLLM minimax_allreduce_rms kernels (#37045)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li
2026-04-11 00:20:20 +08:00
committed by GitHub
parent 8f121f7879
commit ecd1ea1363
14 changed files with 1861 additions and 4 deletions
+2
View File
@@ -307,6 +307,8 @@ set(VLLM_EXT_SRC
"csrc/torch_bindings.cpp")
if(VLLM_GPU_LANG STREQUAL "CUDA")
list(APPEND VLLM_EXT_SRC "csrc/minimax_reduce_rms_kernel.cu")
SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
# Set CUTLASS_REVISION. Used for FetchContent. Also fixes some bogus messages when building.