Commit Graph

19 Commits

Author SHA1 Message Date
1a7eb7da61 Support beam search & parallel generation (#7) 2023-03-10 09:58:21 -08:00
0deacbce6e Implement single_query_cached_kv_attention kernel (#3) 2023-03-01 15:02:19 -08:00
1ce1333573 Set default dtype to half 2023-02-23 21:31:39 +00:00
fdd0f2f472 Minor 2023-02-23 20:23:47 +00:00
1f6c7ef437 Add controller 2023-02-23 09:32:19 +00:00
343cea3dbc Add seq_ids to input metadata 2023-02-23 09:25:01 +00:00
4b1ac23f53 Fix slot mapping 2023-02-23 00:10:07 +00:00
8290fce47d Add Worker class 2023-02-22 19:01:38 +00:00
709a69176e Move worker/models -> models 2023-02-22 18:03:48 +00:00
6f058c7ba8 Implement cache ops 2023-02-16 07:47:03 +00:00
a1c67e6db8 Minor 2023-02-16 01:42:53 +00:00
9e68a6827e Fix return type error 2023-02-16 01:33:03 +00:00
8edcabc737 Add warning 2023-02-16 01:28:17 +00:00
2f4887de77 Fix KVCache shape 2023-02-16 01:24:45 +00:00
ee9442518d Fix get_model 2023-02-13 22:51:03 +00:00
fffa2e1f4b Add model_utils 2023-02-13 09:36:12 +00:00
bb59a3e730 Fix cache engine 2023-02-13 09:35:48 +00:00
e7bee2aa81 Add cache engine 2023-02-09 11:28:02 +00:00
39161c98a0 Add OPT 2023-02-09 11:25:37 +00:00