apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

supports internode_ll_two_stage (#4162)

Browse Source 
* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports D internode_ll_two_stage

* fix codestype

* fix xpu internode_ll_two_stage

* fix xpu internode_ll_two_stage
This commit is contained in:
lzy
2025-11-04 16:35:40 +08:00
committed by GitHub
parent 8a40374bfe
commit af7e0f27f3
6 changed files with 165 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/engine/engine.py
View File

@@ -563,6 +563,7 @@ class LLMEngine:
"dynamic_load_weight": self.cfg.load_config.dynamic_load_weight,
"disable_any_whitespace": self.cfg.structured_outputs_config.disable_any_whitespace,
"disable_custom_all_reduce": self.cfg.parallel_config.disable_custom_all_reduce,
"use_internode_ll_two_stage": self.cfg.parallel_config.use_internode_ll_two_stage,
"enable_logprob": self.cfg.model_config.enable_logprob,
"lm_head_fp32": self.cfg.model_config.lm_head_fp32,
}