2 Commits (fced14025043e29ce816b315f440601188f7f79f)

Author	SHA1	Message	Date
Jianghai	fced140250	[inference] Async dynamic batching (#4894) ... * finish input and output logic * add generate * test forward * 1	2023-10-12 18:48:27 +08:00
Jianghai	e0757c31fb	[inference] Dynamic Batching for Single and Multiple GPUs (#4831) ... * finish batch manager * 1 * first * fix * fix dynamic batching * llama infer * finish test * support different lengths generating * del prints * del prints * fix * fix bug --------- Co-authored-by: CjhHa1 <cjh18671720497outlook.com>	2023-10-11 17:52:52 +08:00