• Bin Jia's avatar
    [Pipeline Inference] Merge pp with tp (#4993) · b6696beb
    Bin Jia authored
    * 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
    b6696beb
test_pipeline_infer.py 2.98 KB