Commit Graph
19 Commits
Author SHA1 Message Date
Yanming W 8efe23f150 Fix input_metadata.selected_token_indices in worker prepare_inputs (#1546) 2023-11-08 14:19:12 -08:00
Antoni Baum 9738b84a08 Force paged attention v2 for long contexts (#1510) 2023-11-01 16:24:32 -07:00
Woosuk Kwon 0ce8647dc5 Fix integer overflows in attention & cache ops (#1514) 2023-10-31 15:19:30 -07:00
Antoni Baum 15f5632365 Delay GPU->CPU sync in sampling (#1337) 2023-10-30 09:01:34 -07:00
Woosuk Kwon c1376e0f82 Change scheduler & input tensor shape (#1381) 2023-10-16 17:48:42 -07:00
Antoni Baum ee92b58b3a Move bfloat16 check to worker (#1259) 2023-10-07 22:10:44 -07:00
Woosuk Kwon 2e8e49fce3 [Fix] Remove false assertion (#1222) 2023-09-28 10:52:38 -07:00
Woosuk Kwon a8e98aee0c Fix Mistral model (#1220) 2023-09-28 10:44:05 -07:00
Chris Bamfordandtimlacroix bb1ba58f06 [Mistral] Mistral-7B-v0.1 support (#1196)
Co-authored-by: timlacroix <t@mistral.ai>
2023-09-28 10:41:03 -07:00
Antoni Baum cf5cb1e33e Allocate more shared memory to attention kernel (#1154) 2023-09-26 22:27:13 -07:00
Woosuk Kwon 9f6be8692e Fix config for Falcon (#1164) 2023-09-23 17:38:43 -07:00
Woosuk Kwon 2ac4d5e2bf Replace DtypeTensor (#1123) 2023-09-21 00:51:47 -07:00
Zhuohan Li 002800f081 Align vLLM's beam search implementation with HF generate (#857) 2023-09-04 17:29:42 -07:00
Zhuohan Li 1b0bd0fe8a Add Falcon support (new) (#592) 2023-08-02 14:04:39 -07:00
Antoni Baum 9925c17940 Ray placement group support (#397) 2023-07-19 22:49:31 -07:00
Zhuohan Li d6fa1be3a8 [Quality] Add code formatter and linter (#326) 2023-07-03 11:31:55 -07:00
Zhuohan Li 85de093472 [Fix] Do not pin memory when in WSL (#312) 2023-06-29 15:00:21 -07:00
Zhuohan Li 0b7db411b5 [Bug] Fix the OOM condition for CPU cache (#260) 2023-06-26 11:16:13 -07:00
Woosuk Kwon 0b98ba15c7 Change the name to vLLM (#150) 2023-06-17 03:07:40 -07:00