iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix][Build] Build fused GDN MTP decode for SM80-SM90 with CUDA < 13 (#60896)

Browse Source 
Signed-off-by: kimseunghyun <incongnito12@gmail.com>
Signed-off-by: kimseunghyun <hellonypcteam@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: kimseunghyun <hellonypcteam@gmail.com>
This commit is contained in:
trienebutdiene
2026-10-18 15:14:06 +08:00
committed by GitHub
co-authored by Claude Opus 5.5 Shengqi Chen kimseunghyun
parent 7c9042c05a
commit b510857d37
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CMakeLists.txt
+5
View File
@@ -1119,6 +1119,11 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
"9.0a;10.0f;12.0f" "${CUDA_ARCHS}")
cuda_archs_loose_intersection(FUSED_GDN_DECODE_ARCHS
"8.0;8.6;8.9;9.0a;10.0f;11.0f;12.0f" "${CUDA_ARCHS}")
else()
# The fused GDN decode kernel needs only cp.async and BF16 math. Only the
# family-specific targets (10.0f, 11.0f, 12.0f) need CUDA >= 13.0.
cuda_archs_loose_intersection(FUSED_GDN_DECODE_ARCHS
"8.0;8.6;8.9;9.0a" "${CUDA_ARCHS}")
endif()
if(FUSED_KDA_DECODE_ARCHS)
set(FUSED_KDA_DECODE_SRC