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

Set num_fused_shared_experts as num_shared_experts when shared_experts fusion is not disabled (#6736)

Browse Source
This commit is contained in:
Cheng Wan
2025-06-04 15:53:22 -07:00
committed by GitHub
parent f0f84975f4
commit 81964328b7
22 changed files with 381 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/layers/quantization/w8a8_fp8.py
View File

@@ -287,6 +287,7 @@ class W8A8FP8MoEMethod:
use_grouped_topk: bool,
topk_group: Optional[int] = None,
num_expert_group: Optional[int] = None,
num_fused_shared_experts: int = 0,
custom_routing_function: Optional[Callable] = None,
correction_bias: Optional[torch.Tensor] = None,
activation: str = "silu",
@@ -306,6 +307,7 @@ class W8A8FP8MoEMethod:
renormalize=renormalize,
topk_group=topk_group,
num_expert_group=num_expert_group,
num_fused_shared_experts=num_fused_shared_experts,
custom_routing_function=custom_routing_function,
correction_bias=correction_bias,
routed_scaling_factor=routed_scaling_factor,