256 Commits

Author SHA1 Message Date
Cyrus Leung
686cfd91e3 [mypy] Further improve MM type annotations (#25654)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:55 -07:00
Cyrus Leung
4ca175ea0b [Misc]] Move processing context to multimodal directory (#25548)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Cyrus Leung
215da8510d [Misc] Move DP for ViT code inside model executor dir (#25459)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Cyrus Leung
2f237d3df4 [V0 Deprecation] Remove MultiModalPlaceholderMap (#25366)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Cyrus Leung
243c358fa8 [V0 Deprecation] Remove V0-only methods in multi-modal registry (#25362)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Woosuk Kwon
20235c1822 [V0 Deprecation] Remove from_seq_group methods (#25330)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Wenlong Wang
dad5f4d16d [Docs] Fix warnings in mkdocs build (continued) (#25042)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Cyrus Leung
6c117cff7d
[Frontend] Pass API server count to each process (#23717)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-09-20 01:15:19 +08:00
Michael Yao
6c8a3c099b
[Docs] Fix griffe warnings in vllm/multimodal (#25216)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
2025-09-18 22:10:44 -07:00
Roger Wang
31a8a2a7bc
[Misc] Clean up MM profiling warnings (#25222)
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-09-19 04:46:57 +00:00
Punitvara
05b044e698
[Doc] Fix cross-reference warnings (#25058)
Signed-off-by: Punit Vara <punitvara@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-09-18 02:05:16 -07:00
Lukas Geiger
b98219670f
[Core][MM] Cleanup MultiModalCache (#25006)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-09-17 21:08:41 -07:00
Lukas Geiger
03191cd8f0
[Core][MultiModalHasher] Hash images without converting image mode (#24969)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-09-17 00:57:34 -07:00
Roger Wang
0f7acdd73c
[Model] Support Qwen3-VL Model Series (#24727)
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Huang Jie <92386084+JJJYmmm@users.noreply.github.com>
Co-authored-by: 松灵 <26085463+wulipc@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-17 05:01:04 +00:00
Lukas Geiger
08369289af
[Core][MultiModalHasher] Don't convert memoryviews to bytes during hashing (#24925)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-09-16 15:32:47 +00:00
Woosuk Kwon
759ef49b15
Remove V0 Encoder-Decoder Support (#24907)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
2025-09-15 21:17:14 -07:00
Isotr0py
0e219cd50b
[Bugfix] Fix GLM4.1V multimodal processor with compatability for Transformers v4.56 (#24822)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-15 20:45:06 +08:00
co63oc
1177dd53e9
fix type of sampling rate for encode_base64 (#24826)
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
2025-09-14 16:17:16 +00:00
Chenheli Hua
7f2ea7074e
[Frontend][Multimodal] Allow skipping media data when UUIDs are provided. (#23950)
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.me>
2025-09-13 02:16:06 +00:00
dongluw
a5b84f1cbf
[Core] Shared memory based object store for Multimodal data caching and IPC (#20452)
Signed-off-by: donglu <donglu@cohere.com>
2025-09-12 07:54:17 -07:00
Isotr0py
bcbe2a4d9e
[VLM] Optimize GLM4.5-V-style video processing to only decode necessary frames (#24161)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-11 09:44:34 -07:00
Chenheli Hua
009d689b0c
[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
2025-09-09 21:36:09 -07:00
Isotr0py
9c99e4871f
[Misc] Clean up deadcode for legacy processing pipeline (#24153)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-03 08:34:29 +00:00
Didier Durand
d7e1e59972
[Doc]: fix typos in Python comments (#24093)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
2025-09-02 21:05:45 -07:00
WeiQing Chen
a0e0efd6bd
[Model] Support DP for ViT on Kimi-VL-A3B-Thinking-2506 (#23817)
Signed-off-by: Junhong <liujunhong11@huawei.com>
Signed-off-by: LJH-LBJ <98734602+LJH-LBJ@users.noreply.github.com>
Co-authored-by: Junhong <liujunhong11@huawei.com>
Co-authored-by: LJH-LBJ <98734602+LJH-LBJ@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2025-09-01 16:56:56 +00:00
Roger Wang
749be00a98
[Core][Multimodal] Allow passing multi_modal_uuids as multimodal identifiers. (#23394)
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-08-30 18:01:22 -07:00
Adit Chawdhary
4f7cde7272
Adds json_count_leaves utility function (#23899)
Signed-off-by: aditchawdhary <aditxy@hotmail.com>
2025-08-29 05:28:13 -07:00
Flora Feng
69f46359dd
[Multimodal] Consolidate mm inputs into MultiModalFeatureSpec (#23779)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2025-08-29 18:36:57 +08:00
Maximilien de Bayser
2554b27baa
[V0 Deprecation] Remove pooling model support in V0 (#23434)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-08-29 00:04:02 -07:00
Roger Wang
8bf6266a17
[Multimodal] Generate mm_hash based on request metadata when caching is turned off (#23690)
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-08-27 20:24:31 +00:00
Cyrus Leung
69244e67e6
[Core] Use key-only cache for BaseMultiModalProcessor (#23018)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-27 14:19:13 +08:00
Cyrus Leung
9715f7bb0f
[Bugfix] Fix incorrect original shape in hashing (#23672)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-08-26 19:01:25 +00:00
Russell Bryant
98aa16ff41
[v1] Add cross-attention KV cache support for encoder-decoder models (#23664)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-08-26 18:49:06 +00:00
Yuekai Zhang
513298f1b4
[Bugfix] fix bf16 multimodal model hash (#23623)
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-08-26 23:47:50 +08:00
Cyrus Leung
6879cd80ae
[Refactor] Pass tokenizer explicitly instead of binding to prompt update (#23542)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-25 06:31:57 -07:00
Cyrus Leung
712d0f88d8
[Refactor] Dynamic target and content for prompt updates (#23411)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-24 23:39:58 -07:00
汪志鹏
416f05929a
[New Model]Donut model (#23229)
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2025-08-24 12:52:24 +00:00
WeiQing Chen
23c939fd30
[Model] Support DP for ViT on MiniCPM-V-4 (#23327)
Signed-off-by: ycyaw66 <497410282@qq.com>
Co-authored-by: ycyaw66 <497410282@qq.com>
2025-08-23 02:14:41 +00:00
Roger Wang
79f05e4436
[Multimodal] Always enable hashing mm data (#23308)
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-21 07:23:28 -07:00
TJian
1298c67795
[FEAT] [Performance] Enable DP for ViT in Qwen2.5VL (#22742)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-08-19 15:25:57 +00:00
Cyrus Leung
d3f71f1224
[Refactor] Get prompt updates earlier (#23097)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-18 12:31:53 +00:00
Cyrus Leung
27e8d1ea3e
[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-18 09:52:00 +00:00
Roger Wang
89657a557c
[Misc] Fix backward compatibility from #23030 (#23070)
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.me>
2025-08-17 23:33:29 -07:00
Cyrus Leung
5c32143b9d
[Refactor] Defer tensor data construction in MultiModalKwargs (#23030)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-16 21:05:50 -07:00
Cyrus Leung
4dff91c93d
[Refactor] Allow optional MultiModalKwargsItem in IPC (#23022)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-16 11:30:49 +00:00
Staszek Paśko
22341b996e
Improve multimodal hasher performance for re-used Image prompts (#22825)
Signed-off-by: Staszek Pasko <staszek@gmail.com>
2025-08-15 12:32:56 +00:00
Sayandip Dutta
aa300c438d
[Bugfix] Unquote file uri before reading image (#22912)
Signed-off-by: Sayandip Dutta <sayandip199309@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-08-15 09:28:00 +00:00
Cyrus Leung
19b927e52d
[Core] Use individual MM items in P0/P1 cache and model runner (#22570)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-13 07:18:07 -07:00
milesial
20d65aa755
[Frontend] Multithreaded async multimodal load_bytes (#22710)
Signed-off-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
Co-authored-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
2025-08-13 06:09:26 -07:00
Cyrus Leung
951b038298
[Misc] Move jsontree to utils (#22622)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-11 03:49:32 -07:00