Update marlin moe kernel interface (#13322)
This commit is contained in:
@@ -34,7 +34,7 @@ from sgl_kernel.elementwise import (
|
||||
silu_and_mul,
|
||||
)
|
||||
from sgl_kernel.expert_specialization import es_fp8_blockwise_scaled_grouped_mm
|
||||
from sgl_kernel.fused_moe import fused_marlin_moe
|
||||
from sgl_kernel.fused_moe import fused_marlin_moe, moe_wna16_marlin_gemm
|
||||
from sgl_kernel.gemm import (
|
||||
awq_dequantize,
|
||||
bmm_fp8,
|
||||
|
||||
Reference in New Issue
Block a user