 Simon Mo
|
acda0b35d0
|
bump version to v0.6.1.post1 (#8440)
|
2024-09-12 21:39:49 -07:00 |
|
|
William Lin
|
ba77527955
|
[bugfix] torch profiler bug for single gpu with GPUExecutor (#8354)
|
2024-09-12 21:30:00 -07:00 |
|
|
Alexander Matveev
|
6821020109
|
[Bugfix] Fix async log stats (#8417)
|
2024-09-12 20:48:59 -07:00 |
|
|
Cyrus Leung
|
5ec9c0fb3c
|
[Core] Factor out input preprocessing to a separate class (#7329)
|
2024-09-13 02:56:13 +00:00 |
|
|
Dipika Sikka
|
8f44a92d85
|
[BugFix] fix group_topk (#8430)
|
2024-09-13 09:23:42 +08:00 |
|
|
Wenxiang
|
a480939e8e
|
[Bugfix] Fix weight loading issue by rename variable. (#8293)
|
2024-09-12 19:25:00 -04:00 |
|
|
Patrick von Platen
|
d31174a4e1
|
[Hotfix][Pixtral] Fix multiple images bugs (#8415)
|
2024-09-12 15:21:51 -07:00 |
|
|
Roger Wang
|
c16369455f
|
[Hotfix][Core][VLM] Disable chunked prefill by default and prefix caching for multimodal models (#8425)
|
2024-09-12 14:06:51 -07:00 |
|
|
Alexander Matveev
|
019877253b
|
[Bugfix] multi-step + flashinfer: ensure cuda graph compatible (#8427)
|
2024-09-12 21:01:50 +00:00 |
|
|
Nick Hill
|
551ce01078
|
[Core] Add engine option to return only deltas or final output (#7381)
|
2024-09-12 12:02:00 -07:00 |
|
|
William Lin
|
a6c0f3658d
|
[multi-step] add flashinfer backend (#7928)
|
2024-09-12 11:16:22 -07:00 |
|
|
Joe Runde
|
f2e263b801
|
[Bugfix] Offline mode fix (#8376)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
|
2024-09-12 11:11:57 -07:00 |
|
|
Luis Vega
|
1f0c75afa9
|
[BugFix] Fix Duplicate Assignment in Hermes2ProToolParser (#8423)
|
2024-09-12 11:10:11 -07:00 |
|
|
WANGWEI
|
8a23e93302
|
[BugFix] lazy init _copy_stream to avoid torch init wrong gpu instance (#8403)
|
2024-09-12 10:47:42 -07:00 |
|
|
|
c6202daeed
|
[Model] Support multiple images for qwen-vl (#8247)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-09-12 10:10:54 -07:00 |
|
|
Isotr0pyandDarkLight1337
|
e56bf27741
|
[Bugfix] Fix InternVL2 inference with various num_patches (#8375)
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-09-12 10:10:35 -07:00 |
|
|
Roger Wang
|
520ca380ae
|
[Hotfix][VLM] Fixing max position embeddings for Pixtral (#8399)
|
2024-09-12 09:28:37 -07:00 |
|
|
youkaichao
|
7de49aa86c
|
[torch.compile] hide slicing under custom op for inductor (#8384)
|
2024-09-12 00:11:55 -07:00 |
|
|
Woosuk Kwon
|
42ffba11ad
|
[Misc] Use RoPE cache for MRoPE (#8396)
|
2024-09-11 23:13:14 -07:00 |
|
|
Kevin Lin
|
295c4730a8
|
[Misc] Raise error when using encoder/decoder model with cpu backend (#8355)
|
2024-09-12 05:45:24 +00:00 |
|
|
Blueyo0
|
1bf2dd9df0
|
[Gemma2] add bitsandbytes support for Gemma2 (#8338)
|
2024-09-11 21:53:12 -07:00 |
|
|
tomeras91
|
5a60699c45
|
[Bugfix]: Fix the logic for deciding if tool parsing is used (#8366)
|
2024-09-12 03:55:30 +00:00 |
|
|
Michael Goin
|
b6c75e1cf2
|
Fix the AMD weight loading tests (#8390)
|
2024-09-11 20:35:33 -07:00 |
|
|
Woosuk Kwon
|
b71c956deb
|
[TPU] Use Ray for default distributed backend (#8389)
|
2024-09-11 20:31:51 -07:00 |
|
|
youkaichao
|
f842a7aff1
|
[misc] remove engine_use_ray (#8126)
|
2024-09-11 18:23:36 -07:00 |
|
|
Cody Yu
|
a65cb16067
|
[MISC] Dump model runner inputs when crashing (#8305)
|
2024-09-12 01:12:25 +00:00 |
|
|
Simon Mo
|
3fd2b0d21c
|
Bump version to v0.6.1 (#8379)
|
2024-09-11 14:42:11 -07:00 |
|
|
Patrick von PlatenandRoger Wang
|
d394787e52
|
Pixtral (#8377)
Co-authored-by: Roger Wang <ywang@roblox.com>
|
2024-09-11 14:41:55 -07:00 |
|
|
Aarni Koskela
|
8baa454937
|
[Misc] Move device options to a single place (#8322)
|
2024-09-11 13:25:58 -07:00 |
|
|
bnellnmandSage Moore
|
73202dbe77
|
[Kernel][Misc] register ops to prevent graph breaks (#6917)
Co-authored-by: Sage Moore <sage@neuralmagic.com>
|
2024-09-11 12:52:19 -07:00 |
|
|
Cyrus Leung
|
7015417fd4
|
[Bugfix] Add missing attributes in mistral tokenizer (#8364)
|
2024-09-11 11:36:54 -07:00 |
|
|
Li, Jiang
|
0b952af458
|
[Hardware][Intel] Support compressed-tensor W8A8 for CPU backend (#7257)
|
2024-09-11 09:46:46 -07:00 |
|
|
|
3b7fea770f
|
[Model][VLM] Add Qwen2-VL model support (#7905)
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-09-11 09:31:19 -07:00 |
|
|
Pooya Davoodi
|
cea95dfb94
|
[Frontend] Create ErrorResponse instead of raising exceptions in run_batch (#8347)
|
2024-09-11 05:30:11 +00:00 |
|
|
|
6a512a00df
|
[model] Support for Llava-Next-Video model (#7559)
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2024-09-10 22:21:36 -07:00 |
|
|
Pavani Majety
|
efcf946a15
|
[Hardware][NV] Add support for ModelOpt static scaling checkpoints. (#6112)
|
2024-09-11 00:38:40 -04:00 |
|
|
Isotr0py
|
1230263e16
|
[Bugfix] Fix InternVL2 vision embeddings process with pipeline parallel (#8299)
|
2024-09-11 10:11:01 +08:00 |
|
|
Jee Jee Li
|
e497b8aeff
|
[Misc] Skip loading extra bias for Qwen2-MOE GPTQ models (#8329)
|
2024-09-10 20:59:19 -04:00 |
|
|
William Lin
|
1d5e397aa4
|
[Core/Bugfix] pass VLLM_ATTENTION_BACKEND to ray workers (#8172)
|
2024-09-10 23:46:08 +00:00 |
|
|
Alexander Matveev
|
22f3a4bc6c
|
[Bugfix] lookahead block table with cuda graph max capture (#8340)
[Bugfix] Ensure multistep lookahead allocation is compatible with cuda graph max capture (#8340)
|
2024-09-10 16:00:35 -07:00 |
|
|
Cody Yu
|
b1f3e18958
|
[MISC] Keep chunked prefill enabled by default with long context when prefix caching is enabled (#8342)
|
2024-09-10 22:28:28 +00:00 |
|
|
Prashant Gupta
|
04e7c4e771
|
[Misc] remove peft as dependency for prompt models (#8162)
|
2024-09-10 17:21:56 -04:00 |
|
|
Kevin Lin
|
5faedf1b62
|
[Spec Decode] Move ops.advance_step to flash attn advance_step (#8224)
|
2024-09-10 13:18:14 -07:00 |
|
|
Cyrus Leung
|
8c054b7a62
|
[Frontend] Clean up type annotations for mistral tokenizer (#8314)
|
2024-09-10 16:49:11 +00:00 |
|
|
Cyrus Leung
|
da1a844e61
|
[Bugfix] Fix missing post_layernorm in CLIP (#8155)
|
2024-09-10 08:22:50 +00:00 |
|
|
Dipika Sikka
|
6cd5e5b07e
|
[Misc] Fused MoE Marlin support for GPTQ (#8217)
|
2024-09-09 23:02:52 -04:00 |
|
|
Kyle Sayers
|
c7cb5c3335
|
[Misc] GPTQ Activation Ordering (#8135)
|
2024-09-09 16:27:26 -04:00 |
|
|
Vladislav Kruglikov
|
f9b4a2d415
|
[Bugfix] Correct adapter usage for cohere and jamba (#8292)
|
2024-09-09 11:20:46 -07:00 |
|
|
Adam LugowskiandAdam Lugowski
|
58fcc8545a
|
[Frontend] Add progress reporting to run_batch.py (#8060)
Co-authored-by: Adam Lugowski <adam.lugowski@parasail.io>
|
2024-09-09 11:16:37 -07:00 |
|
|
Kyle Mistele
|
08287ef675
|
[Bugfix] Streamed tool calls now more strictly follow OpenAI's format; ensures Vercel AI SDK compatibility (#8272)
|
2024-09-09 10:45:11 -04:00 |
|