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/managers/schedule_batch.py
View File

@@ -89,7 +89,7 @@ global_server_args_dict = {
"max_micro_batch_size": ServerArgs.max_micro_batch_size,
"moe_dense_tp_size": ServerArgs.moe_dense_tp_size,
"ep_dispatch_algorithm": ServerArgs.ep_dispatch_algorithm,
"num_fused_shared_experts": ServerArgs.num_fused_shared_experts,
"disable_shared_experts_fusion": ServerArgs.disable_shared_experts_fusion,
"sampling_backend": ServerArgs.sampling_backend,
"speculative_accept_threshold_acc": ServerArgs.speculative_accept_threshold_acc,
"speculative_accept_threshold_single": ServerArgs.speculative_accept_threshold_single,