3 Commits (5ee651c2f1880c7137f93f494e2746557ef87af9)

Author	SHA1	Message	Date
ytxiong	5ee651c2f1	feat(*): support not-flash-attn for pp and no-pp (#145) ... * support not flash attention for no-pp * support pipeline * modify the config * refactor the code * refactor the code * remove some unnecessary code	2023-07-28 16:13:04 +08:00
ytxiong	fd398fae1a	refactor(rotaryEmbedding): refactor forward (#120) ... * use fp16 in instruction (#80) * delete torch_dtype of README's example code (#100) * refactor the forward for rotary embedding --------- Co-authored-by: WRH <12756472+wangruohui@users.noreply.github.com> Co-authored-by: x54-729 <45304952+x54-729@users.noreply.github.com>	2023-07-25 15:25:48 +08:00
Sun Peng	fa7337b37b	initial commit	2023-07-06 12:55:23 +08:00