[Kernel] Adding split_K implementation for fused_moe_lora (#27291)

Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Signed-off-by: Danielle Robinson <dcmaddix@gmail.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
2025-10-27 02:05:24 -07:00
committed by GitHub
co-authored by Danielle Robinson Jee Jee Li
parent 2d631d28c6
commit 9932ed6a83
4 changed files with 35 additions and 14 deletions
+2
View File
@@ -154,6 +154,7 @@ def use_fused_moe_lora_kernel(
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"SPLIT_K": 1,
}
mul_routed_weight = False
@@ -175,6 +176,7 @@ def use_fused_moe_lora_kernel(
config["BLOCK_SIZE_N"],
config["BLOCK_SIZE_K"],
config["GROUP_SIZE_M"],
config["SPLIT_K"],
mul_routed_weight,
)