biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Set splitk=1 for fused-moe-lora expand kernel (#32882)

Browse Source 
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Danielle Robinson
2026-01-25 22:52:34 -08:00
committed by GitHub
parent a9b53dd435
commit ee484b3f4b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/lora/ops/triton_ops/fused_moe_lora_op.py
View File

@@ -351,7 +351,7 @@ def _fused_moe_lora_expand(
"GROUP_SIZE_M": group_size_m,
"num_warps": num_warps,
"num_stages": num_stages,
"SPLIT_K": split_k, # Set split_k = 1 for expand calls
"SPLIT_K": 1, # Set split_k = 1 for expand calls
"USE_GDC": use_gdc,
"launch_pdl": use_gdc, # triton kernel metadata
}