Commit Graph

81 Commits

Author SHA1 Message Date
fzyzcjy
fd28640dc5 Add update_weights_from_tensor (#2631) 2024-12-28 13:30:27 -08:00
Lianmin Zheng
a6ca736c8e Simplify stream_output (#2398) 2024-12-08 12:27:13 -08:00
Chayenne
983bfcf386 Online weight updates from torch.distributed (#2279) 2024-12-01 23:23:18 -08:00
Chayenne
7d1485d376 Add get weights by parameter name for llama (#2266) 2024-11-29 23:36:38 -08:00
Chayenne
7d5d1d3d29 udate weights from disk (#2265) 2024-11-30 01:17:00 +00:00
Lianmin Zheng
fe97a2d40f Simplify tokenizer manager (#2254) 2024-11-29 02:18:51 -08:00
Rin Intachuen
1aea19f64b Input_embeds support (#2052) 2024-11-25 16:35:04 -08:00
Ying Sheng
e1e595d702 [feat] Refactor session control interface and add CI (#2173) 2024-11-25 12:32:51 -08:00
Xuehai Pan
62a4a339eb docs: fix module docstrings and copyright headers (#2077) 2024-11-22 22:16:53 +08:00
Ying Sheng
5942dfc00a [feat] Add session control (#2073) 2024-11-20 00:36:53 -08:00
Lianmin Zheng
befc6beb86 Fix a typo in io_struct.py (#2008) 2024-11-11 16:34:10 -08:00
Chayenne
c77c1e05ba fix black in pre-commit (#1940) 2024-11-08 07:42:47 +08:00
Lianmin Zheng
2ce32db6fb Let reward model take text inputs instead of message lists (#1907)
Co-authored-by: Kyle Corbitt <kyle@corbt.com>
2024-11-03 13:27:12 -08:00
Lianmin Zheng
c17c578108 Simplify tokenizer manager (#1904) 2024-11-03 08:38:26 -08:00
Lianmin Zheng
838dcda162 Simplify tokenizer manager (#1899) 2024-11-03 03:52:38 -08:00
Lianmin Zheng
fb99aaa527 [Fix] Fix --skip-tokenizer-init (#1798) 2024-10-25 18:51:59 -07:00
Ying Sheng
2fce449b1c [API] add get memory pool size (#1760)
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
2024-10-23 07:02:29 +00:00
Lianmin Zheng
7feba41584 Fix failed ci tests on long prompts; Better error messages for embedding models (#1700) 2024-10-17 09:23:29 -07:00
Ying Sheng
2725f8da61 [Minor] Rename no_eos_trim to no_stop_trim (#1661) 2024-10-13 20:30:03 -07:00
Ying Sheng
4876117171 [Fix] fix eos trim inconsistency (#1650) 2024-10-13 01:07:09 -07:00
科英
bbd72bfc86 Add the ability to enable and disable the Profiler via HTTP API. (#1626) 2024-10-11 02:34:25 -07:00
Yiding-Lu
b503881bd2 [Bug] Fix the Image Input of Batch Generation (#1579) 2024-10-11 02:25:04 -07:00
Byron Hsu
521f862d90 Fix runtime.generate when sampling param is not passed (#1582) 2024-10-05 17:59:05 -07:00
Ying Sheng
f202ed9712 [Refactor] Simplify io_struct and tokenizer_manager (#1549) 2024-10-01 10:25:32 -07:00
Lianmin Zheng
f86c1e611f Move scheduler code from tp_worker.py to scheduler.py (#1538) 2024-09-29 17:42:45 -07:00
Liangsheng Yin
fd9ad817ec Organize image inputs (#1531) 2024-09-29 06:28:55 +00:00
Ying Sheng
9aa6553d2a [Feature] Support reward model LxzGordon/URM-LLaMa-3.1-8B (#1525) 2024-09-27 23:32:11 -07:00
Xiao Yu
5752f25eef Fixed n>1 causing list index out of range with VLM (#1449) 2024-09-18 00:46:32 -07:00
Lianmin Zheng
9ba1f09760 [Fix] Fix logprob and normalized_logprob (#1428) 2024-09-15 06:36:06 -07:00
Ying Sheng
712216928f [Feature] Initial support for multi-LoRA serving (#1307) 2024-09-12 16:46:14 -07:00
wangchao
fec2d1223c [Fix] fix bug of undefined is_single in meth create_abort_task (#1370) 2024-09-10 01:17:37 -07:00
Kaichen Zhang - NTU
662ecd9368 [Feat] Add modalities for vision server when handling pixel values for llava (#1346) 2024-09-09 02:07:34 -07:00
Zhiqiang Xie
8153168c96 fix data racing due to mutable reference using deepcopy (#1255) 2024-08-28 18:57:54 -07:00
Lianmin Zheng
bf53bf5142 [Fix] Fix llava on multi images (#1247) 2024-08-28 06:33:05 -07:00
Liangsheng Yin
83e23c69b3 Improve code style of sampler (#1168) 2024-08-21 16:48:24 -07:00
Shan Yu
cd10654e7e [Feat] Support update weights without restart server (#1157) 2024-08-20 13:48:24 -07:00
yichuan~
b997a18d74 [Feat]Add support for optional start len of logprobs (#1035)
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
2024-08-18 23:45:41 -07:00
Lianmin Zheng
cdc8d60752 Improve the code style: more comments and remove useless packages (#1139) 2024-08-17 14:37:52 -07:00
Ying Sheng
b68c4c073b fix: force max new tokens to be 1 for embedding request (#1019) 2024-08-10 13:46:42 -07:00
Ying Sheng
b16e856f11 Add openai embedding API (#997) 2024-08-09 11:19:18 -07:00
Ying Sheng
20a4f927dc Add io struct for embedding models [unreachable code] - step 2/3 (#987) 2024-08-08 07:52:31 +00:00
yichuan~
d53dcf9c98 Support more OpenAI API test (#916) 2024-08-04 16:43:09 -07:00
Liangsheng Yin
cdcbde5fc3 Code structure refactor (#807) 2024-07-29 23:04:48 -07:00
yichuan~
084fa54d37 Add support for OpenAI API : offline batch(file) processing (#699)
Co-authored-by: hnyls2002 <hnyls2002@gmail.com>
2024-07-29 13:07:18 -07:00
Yineng Zhang
dd7e8b9421 chore: add copyright for srt (#790) 2024-07-28 23:07:12 +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
Yineng Zhang
6b32bb1c0b misc: format (#741) 2024-07-26 21:00:51 +10:00
Toshiki Kataoka
da504445dc fix /generate without sampling_params (#734) 2024-07-26 01:27:56 -07:00
Liangsheng Yin
f424e76d96 Fix illegal tokens during sampling (#676) 2024-07-20 03:11:15 -07:00
Lianmin Zheng
35759efa91 Support random dataset in bench_serving.py (#669) 2024-07-20 01:06:43 -07:00