12 Commits

Author	SHA1	Message	Date
Woosuk Kwon	f8a1e39fae	[BugFix] Define __eq__ in SequenceGroupOutputs (#1389)	2023-10-17 01:09:44 -07:00
Zhuohan Li	9d9072a069	Implement prompt logprobs & Batched topk for computing logprobs (#1328) ... Co-authored-by: Yunmo Chen <16273544+wanmok@users.noreply.github.com>	2023-10-16 10:56:50 -07:00
Wang Ran (汪然)	ac5cf86aa6	Fix __repr__ of SequenceOutputs (#1311)	2023-10-10 09:58:28 -07:00
Zhuohan Li	6b5296aa3a	[FIX] Explain why the finished_reason of ignored sequences are length (#1289)	2023-10-08 15:22:38 -07:00
Zhuohan Li	f029ef94d7	Fix get_max_num_running_seqs for waiting and swapped seq groups (#1068)	2023-09-18 11:49:40 -07:00
Zhuohan Li	f04908cae7	[FIX] Minor bug fixes (#1035) ... * [FIX] Minor bug fixes * Address review comments	2023-09-13 16:38:12 -07:00
Antoni Baum	9841d48a10	Use TGI-like incremental detokenization (#984)	2023-09-13 13:38:01 -07:00
Zhuohan Li	002800f081	Align vLLM's beam search implementation with HF generate (#857)	2023-09-04 17:29:42 -07:00
Lily Liu	2179e4f4c5	avoid python list copy in sequence initialization (#401)	2023-07-08 12:42:08 -07:00
Zhuohan Li	d6fa1be3a8	[Quality] Add code formatter and linter (#326)	2023-07-03 11:31:55 -07:00
Lily Liu	dafd924c1f	Raise error for long prompt (#273)	2023-06-30 18:48:49 -07:00
Woosuk Kwon	0b98ba15c7	Change the name to vLLM (#150)	2023-06-17 03:07:40 -07:00