apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend (#3148)

Browse Source 
* w4a8 bug

* fix w4a8 bug

* remove code

* modify the triton backend

* fix ep

* fix the bug with tensor_wise_fp8 in triton backend

* fix the RL

* fix bug by merge

* fix the bug in w4a8

* fix the tensor_wise_fp8 bug

* fix RL
This commit is contained in:
Zero Rains
2025-08-08 15:55:47 +08:00
committed by GitHub
parent d0e9a70380
commit ce1f353c70
10 changed files with 444 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/engine/expert_service.py
View File

@@ -59,8 +59,8 @@ class ExpertService:
self.cfg.disaggregate_info = None
self.scheduler = cfg.scheduler_config.scheduler()
self.scheduler.reset_nodeid(f"{self.scheduler.infer.nodeid}_{local_data_parallel_id!s}")
if cfg.splitwise_role != "mixed":
self.scheduler.reset_nodeid(f"{self.scheduler.infer.nodeid}_{local_data_parallel_id!s}")
self.cfg.parallel_config.local_data_parallel_id = local_data_parallel_id