wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-08-14 12:50:37 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,089 Commits 1 Branch 0 Tags
96b6a6d790115d04bb87d410f3bdd5d7d85b43f1
Commit Graph
8 Commits
Author SHA1 Message Date
Nick Hill e46a60aa4c [BugFix] Fix handling of stop strings and stop token ids (#3672) 2024-04-11 15:34:12 -07:00
Matthias GerstgrasserandNick Hill aabe8f40f2 [Core] [Frontend] Make detokenization optional (#3749) 
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
 2024-04-03 21:52:18 -07:00
Antoni Baum fb96c1e98c Asynchronous tokenization (#2879) 2024-03-15 23:37:01 +00:00
ElizaWszola b35cc93420 Fix auto prefix bug (#3239) 2024-03-07 16:37:28 -08:00
Simon Mo 5ffc0d13a2 Migrate linter from pylint to ruff (#1665) 2023-11-20 11:58:01 -08:00
Zhuohan Li ba0bfd40e2 TP/quantization/weight loading refactor part 1 - Simplify parallel linear logic (#1181) 2023-10-02 15:36:09 -07:00
Antoni Baum dd54a4b026 Fix detokenization leaving special tokens (#1044) 
Signed-off-by: Antoni Baum <antoni.baum@protonmail.com>
 2023-09-14 16:37:03 -07:00
Antoni Baum 9841d48a10 Use TGI-like incremental detokenization (#984) 2023-09-13 13:38:01 -07:00