• Hongxin Liu's avatar
    [gemini] accelerate inference (#3641) · 50793b35
    Hongxin Liu authored
    * [gemini] support don't scatter after inference
    
    * [chat] update colossalai strategy
    
    * [chat] fix opt benchmark
    
    * [chat] update opt benchmark
    
    * [gemini] optimize inference
    
    * [test] add gemini inference test
    
    * [chat] fix unit test ci
    
    * [chat] fix ci
    
    * [chat] fix ci
    
    * [chat] skip checkpoint test
    50793b35
__init__.py 440 Bytes