chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

Add DeepSeek V3/R1 shared experts fusion (#4918)

Browse Source
This commit is contained in:
Xiaoyu Zhang
2025-04-04 16:59:29 +08:00
committed by GitHub
parent 6ff9c6a5e7
commit 924ca7c92c
14 changed files with 536 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
python/sglang/srt/layers/quantization/__init__.py
View File

@@ -51,7 +51,6 @@ except ImportError:
from sglang.srt.layers.linear import LinearBase, UnquantizedLinearMethod
from sglang.srt.layers.moe.fused_moe_triton.layer import FusedMoE
from sglang.srt.layers.quantization.awq import AWQConfig
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.layers.quantization.blockwise_int8 import BlockInt8Config
@@ -203,6 +202,8 @@ def get_linear_quant_method(
def gptq_get_quant_method(self, layer, prefix):
from sglang.srt.layers.moe.fused_moe_triton.layer import FusedMoE
if isinstance(layer, FusedMoE):
return GPTQMarlinMoEMethod(self)