[Pipeline Inference] Merge pp with tp (#4993)

* refactor pipeline into new CaiInferEngine

* updata llama modeling forward

* merge tp with pp

* update docstring

* optimize test workflow and example

* fix typo

* add assert and todo
This commit is contained in:
Bin Jia
2023-11-01 12:46:21 +08:00
committed by GitHub
parent 335cb105e2
commit b6696beb04
12 changed files with 268 additions and 203 deletions

View File

@@ -1,4 +1,4 @@
from .pipeline import PPInferEngine
from .hybridengine import CaiInferEngine
from .hybridengine.polices import LlamaModelInferPolicy
__all__ = ['PPInferEngine']
__all__ = ["CaiInferEngine", "LlamaModelInferPolicy"]