wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-14 11:19:39 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,328 Commits 1 Branch 0 Tags
8bc68e198c4c90ddc2e54fa76eb81c2c714bb1cd
Commit Graph
10 Commits
Author SHA1 Message Date
Cody YuandGitHub bc8ad68455 [Misc][Refactor] Introduce ExecuteModelData (#4540) 2024-05-03 17:47:07 -07:00
Cade DanielandGitHub ab50275111 [Speculative decoding] Support target-model logprobs (#4378) 2024-05-03 15:52:01 -07:00
SangBin ChoandGitHub 3521ba4f25 [Core][Model runner refactoring 1/N] Refactor attn metadata term (#4518) 2024-05-03 10:20:12 -07:00
leiwen83GitHubLei Wen
 		b38e42fbca [Speculative decoding] Add ngram prompt lookup decoding (#4237) 
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
 2024-05-01 11:13:03 -07:00
Cade DanielandGitHub 62b8aebc6f [Speculative decoding 7/9] Speculative decoding end-to-end correctness tests. (#3951) 2024-04-23 08:02:36 +00:00
Cade DanielandGitHub e95cd87959 [Speculative decoding 6/9] Integrate speculative decoding with LLMEngine (#3894) 2024-04-16 13:09:21 -07:00
SangBin ChoandGitHub 01bfb22b41 [CI] Try introducing isort. (#3495) 2024-03-25 07:59:47 -07:00
SangBin ChoandGitHub 6e435de766 [1/n][Chunked Prefill] Refactor input query shapes (#3236) 2024-03-20 14:46:05 -07:00
Zhuohan LiandGitHub 2f8844ba08 Re-enable the 80 char line width limit (#3305) 2024-03-10 19:49:14 -07:00
Cade DanielandGitHub 8437bae6ef [Speculative decoding 3/9] Worker which speculates, scores, and applies rejection sampling (#3103) 2024-03-08 23:32:46 -08:00