113 Commits

Author SHA1 Message Date
Simon Mo
a134ef6f5e
Support eos_token_id from generation_config.json (#4182) 2024-04-19 04:13:36 +00:00
Cade Daniel
e95cd87959
[Speculative decoding 6/9] Integrate speculative decoding with LLMEngine (#3894) 2024-04-16 13:09:21 -07:00
Antoni Baum
69e1d2fb69
[Core] Refactor model loading code (#4097) 2024-04-16 11:34:39 -07:00
Noam Gat
05434764cd
LM Format Enforcer Guided Decoding Support (#3868)
Co-authored-by: Simon Mo <simon.mo@hey.com>
2024-04-16 05:54:57 +00:00
Sanger Steel
711a000255
[Frontend] [Core] feat: Add model loading using tensorizer (#3476) 2024-04-13 17:13:01 -07:00
Nick Hill
e46a60aa4c
[BugFix] Fix handling of stop strings and stop token ids (#3672) 2024-04-11 15:34:12 -07:00
SangBin Cho
67b4221a61
[Core][5/N] Fully working chunked prefill e2e (#3884) 2024-04-10 17:56:48 -07:00
Cade Daniel
e7c7067b45
[Misc] [Core] Implement RFC "Augment BaseExecutor interfaces to enable hardware-agnostic speculative decoding" (#3837) 2024-04-09 11:44:15 -07:00
SangBin Cho
18de883489
[Chunked Prefill][4/n] Chunked prefill scheduler. (#3853) 2024-04-05 10:17:58 -07:00
Matthias Gerstgrasser
aabe8f40f2
[Core] [Frontend] Make detokenization optional (#3749)
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-04-03 21:52:18 -07:00
Adrian Abeyta
2ff767b513
Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: HaiShaw <hixiao@gmail.com>
Co-authored-by: AdrianAbeyta <Adrian.Abeyta@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: root <root@gt-pla-u18-08.pla.dcgpu>
Co-authored-by: mawong-amd <156021403+mawong-amd@users.noreply.github.com>
Co-authored-by: ttbachyinsda <ttbachyinsda@outlook.com>
Co-authored-by: guofangze <guofangze@kuaishou.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: jacobthebanana <50071502+jacobthebanana@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-04-03 14:15:55 -07:00
SangBin Cho
3dcb3e8b98
[3/N] Refactor scheduler for chunked prefill scheduling (#3550) 2024-04-03 14:13:49 -07:00
Cade Daniel
5757d90e26
[Speculative decoding] Adding configuration object for speculative decoding (#3706)
Co-authored-by: Lily Liu <lilyliupku@gmail.com>
2024-04-03 00:40:57 +00:00
leiwen83
ad6eca408b
Fix early CUDA init via get_architecture_class_name import (#3770)
Signed-off-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
2024-04-02 11:56:26 -07:00
bigPYJ1151
0e3f06fe9c
[Hardware][Intel] Add CPU inference backend (#3634)
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Yuan Zhou <yuan.zhou@intel.com>
2024-04-01 22:07:30 -07:00
Roy
6110c39dc8
[BugFix] Fix tokenizer out of vocab size (#3685) 2024-03-29 08:18:59 -07:00
yhu422
d8658c8cc1
Usage Stats Collection (#2852) 2024-03-28 22:16:12 -07:00
SangBin Cho
b51c1cc9d2
[2/N] Chunked prefill data update (#3538) 2024-03-28 10:06:01 -07:00
Cade Daniel
14ccd94c89
[Core][Bugfix]Refactor block manager for better testability (#3492) 2024-03-27 23:59:28 -07:00
Nick Hill
dfeb2ecc3a
[Misc] Include matched stop string/token in responses (#2976)
Co-authored-by: Sahil Suneja <sahilsuneja@gmail.com>
2024-03-25 17:31:32 -07:00
xwjiang2010
64172a976c
[Feature] Add vision language model support. (#3042) 2024-03-25 14:16:30 -07:00
Travis Johnson
c13ad1b7bd
feat: implement the min_tokens sampling parameter (#3124)
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-03-25 10:14:26 -07:00
SangBin Cho
01bfb22b41
[CI] Try introducing isort. (#3495) 2024-03-25 07:59:47 -07:00
Antoni Baum
bfdb1ba5c3
[Core] Improve detokenization performance for prefill (#3469)
Co-authored-by: MeloYang <meloyang05@gmail.com>
2024-03-22 13:44:12 -07:00
Zhuohan Li
e90fc21f2e
[Hardware][Neuron] Refactor neuron support (#3471) 2024-03-22 01:22:17 +00:00
Roy
865732342b
[Misc][Log] Add log for tokenizer length not equal to vocabulary size (#3500) 2024-03-21 18:07:48 +08:00
SangBin Cho
6e435de766
[1/n][Chunked Prefill] Refactor input query shapes (#3236) 2024-03-20 14:46:05 -07:00
Antoni Baum
fb96c1e98c
Asynchronous tokenization (#2879) 2024-03-15 23:37:01 +00:00
Tao He
14b8ae02e7
Fixes the misuse/mixuse of time.time()/time.monotonic() (#3220)
Signed-off-by: Tao He <sighingnow@gmail.com>
Co-authored-by: simon-mo <simon.mo@hey.com>
2024-03-15 18:25:43 +00:00
Zhuohan Li
4c922709b6
Add distributed model executor abstraction (#3191) 2024-03-11 11:03:45 -07:00
Zhuohan Li
2f8844ba08
Re-enable the 80 char line width limit (#3305) 2024-03-10 19:49:14 -07:00
Roy
9e8744a545
[BugFix] Fix get tokenizer when using ray (#3301) 2024-03-10 19:17:16 -07:00
Nick Hill
2efce05dc3
[Fix] Avoid pickling entire LLMEngine for Ray workers (#3207)
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2024-03-06 00:17:20 +00:00
Nick Hill
8999ec3c16
Store eos_token_id in Sequence for easy access (#3166) 2024-03-05 15:35:43 -08:00
Antoni Baum
ff578cae54
Add health check, make async Engine more robust (#3015)
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-03-04 22:01:40 +00:00
Antoni Baum
22de45235c
Push logprob generation to LLMEngine (#3065)
Co-authored-by: Avnish Narayan <avnish@anyscale.com>
2024-03-04 19:54:06 +00:00
Philipp Moritz
17c3103c56
Make it easy to profile workers with nsight (#3162)
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-03-03 16:19:13 -08:00
Jason Cox
d65fac2738
Add vLLM version info to logs and openai API server (#3161) 2024-03-02 21:00:29 -08:00
Sage Moore
ce4f5a29fb
Add Automatic Prefix Caching (#2762)
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-03-02 00:50:01 -08:00
Sherry
54d3544784
Fix: Output text is always truncated in some models (#3016) 2024-03-01 07:52:22 +00:00
Nick Hill
29a8d6a554
[Fix] Don't deep-copy LogitsProcessors when copying SamplingParams (#3099) 2024-02-29 19:20:42 +00:00
Allen.Dou
9289e577ec
add cache_config's info to prometheus metrics. (#3100) 2024-02-29 06:15:18 +00:00
Liangfu Chen
3b7178cfa4
[Neuron] Support inference with transformers-neuronx (#2569) 2024-02-28 09:34:34 -08:00
Roy
c1c0d00b88
Don't use cupy when enforce_eager=True (#3037) 2024-02-26 17:33:38 -08:00
Harry Mellor
ef978fe411
Port metrics from aioprometheus to prometheus_client (#2730) 2024-02-25 11:54:00 -08:00
Ronen Schaffer
4caf7044e0
Include tokens from prompt phase in counter_generation_tokens (#2802) 2024-02-22 14:00:12 -08:00
Antoni Baum
017d9f1515
Add metrics to RequestOutput (#2876) 2024-02-20 21:55:57 -08:00
Ronen Schaffer
e433c115bc
Fix vllm:prompt_tokens_total metric calculation (#2869) 2024-02-18 23:55:41 -08:00
Nick Hill
185b2c29e2
Defensively copy sampling_params (#2881)
If the SamplingParams object passed to LLMEngine.add_request() is mutated after it returns, it could affect the async sampling process for that request.

Suggested by @Yard1 https://github.com/vllm-project/vllm/pull/2514#discussion_r1490106059
2024-02-17 11:18:04 -08:00
Woosuk Kwon
a463c333dd
Use CuPy for CUDA graphs (#2811) 2024-02-13 11:32:06 -08:00