EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 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/model_executor/model_runner.py
View File

@@ -204,7 +204,7 @@ class ModelRunner:
"flashinfer_mla_disable_ragged": server_args.flashinfer_mla_disable_ragged,
"moe_dense_tp_size": server_args.moe_dense_tp_size,
"ep_dispatch_algorithm": server_args.ep_dispatch_algorithm,
"num_fused_shared_experts": server_args.num_fused_shared_experts,
"disable_shared_experts_fusion": server_args.disable_shared_experts_fusion,
"triton_attention_reduce_in_fp32": server_args.triton_attention_reduce_in_fp32,
"torchao_config": server_args.torchao_config,
"sampling_backend": server_args.sampling_backend,