chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Refactor] move deep_gemm_wrapper out of quantization (#11784)

Browse Source
This commit is contained in:
Cheng Wan
2025-10-17 18:57:54 -07:00
committed by GitHub
parent 13219e1e48
commit 5b214b50b6
19 changed files with 18 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/models/longcat_flash.py
+1 -1
View File
@@ -44,6 +44,7 @@ from sglang.srt.distributed import (
)
from sglang.srt.eplb.expert_distribution import get_global_expert_distribution_recorder
from sglang.srt.eplb.expert_location import ModelConfigForExpertLocation
from sglang.srt.layers import deep_gemm_wrapper
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.communicator import LayerCommunicator, LayerScatterModes
from sglang.srt.layers.dp_attention import (
@@ -62,7 +63,6 @@ from sglang.srt.layers.moe.ep_moe.kernels import zero_experts_compute_triton
from sglang.srt.layers.moe.ep_moe.layer import DeepEPMoE, get_moe_impl_class
from sglang.srt.layers.moe.fused_moe_triton.layer import FusedMoE
from sglang.srt.layers.moe.topk import StandardTopKOutput, TopK
from sglang.srt.layers.quantization import deep_gemm_wrapper
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.layers.quantization.fp8_kernel import is_fp8_fnuz
from sglang.srt.layers.quantization.fp8_utils import (