Delete sgl-kernel AOT router GEMM and fused A GEMM (#30280)
Co-authored-by: Brayden Zhong <brayden@radixark.ai> Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
This commit is contained in:
co-authored by
Brayden Zhong
root
parent
8ae0eb83fc
commit
03342e7732
@@ -55,7 +55,6 @@ else:
|
||||
)
|
||||
from sgl_kernel.gemm import (
|
||||
awq_dequantize,
|
||||
dsv3_fused_a_gemm,
|
||||
fp8_scaled_mm,
|
||||
gptq_gemm,
|
||||
gptq_shuffle,
|
||||
@@ -160,8 +159,6 @@ else:
|
||||
"copy_to_gpu_no_ce",
|
||||
"cutlass_mla_decode",
|
||||
"cutlass_mla_get_workspace_size",
|
||||
"dsv3_fused_a_gemm",
|
||||
"dsv3_router_gemm",
|
||||
"dsv4_fused_k_norm_rope_flashmla",
|
||||
"dsv4_fused_q_indexer_rope_hadamard_quant",
|
||||
"dsv4_fused_q_norm_rope",
|
||||
|
||||
Reference in New Issue
Block a user