Steve Luo 7806842f2d add paged-attetionv2: support seq length split across thread block (#5707)		2024-05-14 12:46:54 +08:00
..
layers	[Inference] Adapt Baichuan2-13B TP (#5659)	2024-04-30 15:47:07 +08:00
models	add paged-attetionv2: support seq length split across thread block (#5707)	2024-05-14 12:46:54 +08:00
policy	[Feat]Inference RPC Server Support (#5705)	2024-05-14 10:00:55 +08:00
__init__.py	[doc] updated inference readme (#5343)	2024-02-02 14:31:10 +08:00