Commit Graph

86 Commits

Author SHA1 Message Date
Lianmin Zheng
899cf5c438 Remove deprecated configs (#1431) 2024-09-15 08:52:18 -07:00
Lianmin Zheng
9ba1f09760 [Fix] Fix logprob and normalized_logprob (#1428) 2024-09-15 06:36:06 -07:00
Lianmin Zheng
f64eae3a29 [Fix] Reduce memory usage for loading llava model & Remove EntryClassRemapping (#1308) 2024-09-02 21:44:45 -07:00
Max Shawabkeh
6def9b018c Fix hang when doing s += None. (#1297)
Co-authored-by: max99x <mshawabkeh@jamandtea.studio>
2024-09-01 21:56:33 -07:00
Enrique Shockwave
6c34d6339c make json_schema usable from gen (#1254) 2024-08-28 18:57:10 -07:00
Lianmin Zheng
f6af3a6561 Cleanup readme, llava examples, usage examples and nccl init (#1194) 2024-08-24 08:02:23 -07:00
Kaichen Zhang - NTU
a5b14ad043 [Feat/WIP] add llava-onevision, with support for (1) siglip encoder, (2) qwen2 decoder (3) openai api compatible server. (#1123)
Co-authored-by: Bo Li <drluodian@gmail.com>
2024-08-23 14:11:16 -07:00
intervitens
068e9eae55 Support min-p sampling (#1167) 2024-08-21 22:49:32 +00:00
Liangsheng Yin
73cf6834f2 Support stop_token_ids in sglang API (#1092) 2024-08-15 00:31:39 +00:00
Liangsheng Yin
a34dd86a7d Use dtype to control generate (#1082)
Co-authored-by: zhyncs <me@zhyncs.com>
2024-08-14 15:58:07 +00:00
foszto
c62d560c03 #590 Increase default , track changes in examples and documentation (#971)
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
2024-08-08 00:54:46 +00:00
Ke Bao
a9c833d580 Fix union operator (#940) 2024-08-06 00:46:34 +08:00
Aidan Cooper
94e0115186 Feat: add alternative choices selection methods (#835) 2024-08-05 03:27:49 -07:00
Aidan Cooper
b216a545b3 Remove leftover auth_token (#934) 2024-08-05 03:25:48 -07:00
Ying Sheng
0d4f3a9fcd Make API Key OpenAI-compatible (#917) 2024-08-04 13:35:44 -07:00
Ying Sheng
6f221d4ca0 Fix unit tests for the frontend language part (#872) 2024-08-01 12:39:12 -07:00
Kai Fronsdal
0c0c81372e Fix #857 (#858) 2024-08-01 00:05:39 -07:00
ObjectNotFound
daf593a385 Fix streaming bug (#820) 2024-07-30 00:32:07 -07:00
Enrique Shockwave
21e22b9e96 Fix LiteLLM kwargs (#817) 2024-07-29 22:38:02 -07:00
ObjectNotFound
8f6274c82b Add role documentation, add system begin & end tokens (#793) 2024-07-28 23:02:49 -07:00
Ying Sheng
325a06c2de Fix logging (#796) 2024-07-28 23:01:45 -07:00
Yineng Zhang
948625799e docs: init readthedocs support (#783) 2024-07-28 16:50:31 +10:00
Lianmin Zheng
30db99b3d9 Rename prefill_token_logprobs -> input_token_logprobs; decode_token_logprobs -> output_token_logprobs (#776) 2024-07-27 19:50:34 -07:00
Max Shawabkeh
5ad033a070 Fix StreamExecutor.fork() losing the current role start index. (#684) 2024-07-20 23:32:11 -07:00
Ying Sheng
51fda1439f Update Readme (#660)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2024-07-19 09:54:01 -07:00
Liangsheng Yin
564a898ad9 Optimize mem indices mangement (#619) 2024-07-13 23:39:37 -07:00
胡译文
02b7258658 [Feat] Expose logprob options to sgl.gen API (#503)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2024-07-09 00:35:39 -07:00
prophe
d557e9f3b7 Update chat template for qwen and yi-1.5. (#530) 2024-07-08 23:55:44 -07:00
Mingyi
c0982ac553 Fix Llava model (#594) 2024-07-06 00:58:46 -07:00
Ying Sheng
dc1b8bcfaa Format (#593) 2024-07-05 10:06:17 -07:00
Ying Sheng
75b31a2a88 Update run_batch interface and max_prefill_tokens (#574) 2024-06-30 18:26:04 -07:00
sglang
11616fc6bd Minor fix in compiler & format (#545) 2024-06-29 23:42:14 -07:00
Ying Sheng
fb9296f0ed Higher priority for user input of max_prefill_tokens & format (#540) 2024-06-12 21:48:40 -07:00
胡译文
87260b7bfd Litellm Backend (#502) 2024-06-07 12:24:28 -07:00
Lianmin Zheng
ced77c6626 Rename api_num_spec_tokens -> num_api_spec_tokens (#458) 2024-05-20 18:44:23 -07:00
Lianmin Zheng
8dbdc018a3 Abort disconnected requests (#457) 2024-05-20 18:41:21 -07:00
Ying Sheng
3e684be7a3 Fix openai speculative execution (#456) 2024-05-20 17:01:13 -07:00
LiviaSun
ec380dfd30 openai chat speculative execution (#250)
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
2024-05-18 22:23:53 -07:00
Lianmin Zheng
8210ec60f4 Improve error handling & abort disconnected requests (#449) 2024-05-17 05:49:31 -07:00
Liangsheng Yin
690d162d97 Format code (#441) 2024-05-14 22:40:46 +08:00
Yuanhan Zhang
0992d85f92 support llava video (#426) 2024-05-13 16:57:00 -07:00
Lianmin Zheng
5dc55a5f02 Handle truncation errors (#436) 2024-05-13 15:56:00 -07:00
Lianmin Zheng
562b8857d8 Improve error handling (#433) 2024-05-12 20:49:04 -07:00
Qubitium
33b242df30 Compat with latest VLLM 0.4.2 main + fork.number rename + Flashinfer 0.0.4 (#380)
Co-authored-by: ZX <zx@lbx.dev>
Co-authored-by: ZhouXingg <165115237+ZhouXingg@users.noreply.github.com>
2024-05-11 16:37:49 -07:00
Liangsheng Yin
d5de20a3ee Fix sync() when fork(1) (#412) 2024-05-08 15:15:18 +08:00
YoungJoong Noah Kim
4a1c6ae2ce Add Cohere Command R chat template (#411) 2024-05-07 15:18:15 +08:00
Joschka Braun
5c5aba5900 Adding RAG tracing & eval cookbook using Parea (#390) 2024-04-30 16:13:28 -07:00
Liangsheng Yin
150d7020ed Revert removing the unused imports (#385) 2024-04-23 22:36:33 +08:00
Liangsheng Yin
9acc6e3504 add .isort.cfg (#378) 2024-04-22 22:38:09 +08:00
Enrique Shockwave
cf9d8efdd3 llama3 instruct template (#372) 2024-04-21 09:40:12 -07:00