Hongxin Liu f196f40a8f [inference] decouple pipeline logci for chatglm (#5098) ... * [inference] decouple pipeline logci for chatglm * [inference] fix chatglm modeling		2023-11-22 18:26:39 +08:00
..
__init__.py	[inference] Refactor inference architecture (#5057)	2023-11-19 21:05:05 +08:00
_utils.py	[inference] Refactor inference architecture (#5057)	2023-11-19 21:05:05 +08:00
bloom.py	[inference] decouple pipeline logci for bloom (#5097)	2023-11-22 17:49:25 +08:00
chatglm2.py	[inference] decouple pipeline logci for chatglm (#5098)	2023-11-22 18:26:39 +08:00
llama.py	[inference] decouple pp logic for llama (#5092)	2023-11-22 13:53:08 +08:00