Cyrus Leung
57fd13a707
[Bugfix] Fix profiling dummy data for Pixtral ( #18677 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-05-25 14:05:30 +00:00
Harry Mellor
26d0419309
Update deprecated type hinting in models ( #18132 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-05-14 22:06:50 -07:00
Harry Mellor
d6484ef3c3
Add full API docs and improve the UX of navigating them ( #17485 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-05-03 19:42:43 -07:00
Michael Goin
f192ca90e6
Fix PixtralHF missing spatial_merge_size ( #17571 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
2025-05-01 22:14:09 -07:00
Cyrus Leung
506475de5f
[Optim] Compute multimodal hash only once per item ( #17314 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-04-29 09:40:35 +08:00
Michael Goin
cb3f2d8d10
[Bugfix] Fix Mistral3 spatial merge error ( #17270 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
2025-04-27 19:40:05 -07:00
Woosuk Kwon
b411418ff0
[Chore] Remove Sampler from Model Code ( #17084 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
2025-04-24 02:49:33 -07:00
Michael Goin
87b836ba77
Bugfix for PixtralHF models without spatial_merge_size ( #16513 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
2025-04-11 23:32:22 +00:00
Cyrus Leung
56d4aefa33
[VLM] Avoid unnecessary dummy multimodal data during processing ( #16416 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-04-10 19:32:14 +00:00
Cyrus Leung
83b824c8b4
[VLM] Remove BaseProcessingInfo.get_mm_max_tokens_per_item ( #16408 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-04-10 09:06:58 -07:00
Nicolò Lucchesi
d55244df31
[Model] Add SupportsMultiModal.get_language_model interface ( #16007 )
...
Signed-off-by: NickLucche <nlucches@redhat.com >
2025-04-09 04:12:54 -07:00
f2ebb6f541
[V1] Scatter and gather placeholders in the model runner ( #16076 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
Signed-off-by: mgoin <mgoin64@gmail.com >
Signed-off-by: Roger Wang <ywang@roblox.com >
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk >
Co-authored-by: mgoin <mgoin64@gmail.com >
Co-authored-by: Jennifer Zhao <ai.jenniferzhao@gmail.com >
2025-04-08 10:43:41 +08:00
Roger Wang
af51d80fa1
Revert "[V1] Scatter and gather placeholders in the model runner" ( #16075 )
2025-04-04 14:50:57 -07:00
f5722a5052
[V1] Scatter and gather placeholders in the model runner ( #15712 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
Signed-off-by: mgoin <mgoin64@gmail.com >
Signed-off-by: Roger Wang <ywang@roblox.com >
Co-authored-by: mgoin <mgoin64@gmail.com >
Co-authored-by: Roger Wang <ywang@roblox.com >
2025-04-04 21:26:44 +00:00
51d7c6a2b2
[Model] Support Mistral3 in the HF Transformers format ( #15505 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
2025-04-01 06:10:05 -07:00
Cyrus Leung
e6c9053f9e
[Misc] Clean up scatter_patch_features ( #15559 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-27 07:45:00 +00:00
Cyrus Leung
5994430b84
[Misc] Remove redundant num_embeds ( #15443 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-25 18:27:57 +08:00
Cyrus Leung
61f412187d
[Bugfix] Re-enable Gemma3 for V1 ( #14980 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-18 23:58:22 -07:00
Julien Denize
437f9162d0
[Model] Pixtral: Remove layer instantiation duplication ( #15053 )
...
Signed-off-by: Julien Denize <julien.denize@mistral.ai >
2025-03-19 10:34:03 +08:00
Tyler Michael Smith and DarkLight1337
e1eb45d397
[Bugfix] Fix precommit - line too long in pixtral.py ( #14960 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com >
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-17 07:18:50 -07:00
Patrick von Platen
d20b0c139c
Add patch merger ( #14957 )
2025-03-17 06:47:50 -07:00
Rémi Delacourt and DarkLight1337
61c6a5a796
[VLM] Merged multi-modal processor for Pixtral ( #12211 )
...
Signed-off-by: remi <remi@mistral.ai >
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-15 06:28:27 -07:00
Cyrus Leung
ab93f1360f
[VLM] Various cleanup and fixes ( #14806 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-14 05:58:19 -07:00
Cyrus Leung
601bd3268e
[Misc] Clean up type annotation for SupportsMultiModal ( #14794 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-14 00:59:56 -07:00
Cyrus Leung
05fb6718f0
[Bugfix] Clean up multi-modal processors ( #14417 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-03-07 10:33:38 +00:00
lkchen
5d802522a7
[V1][VLM][Pixtral-HF] Support Pixtral-HF on V1 ( #14275 )
...
Signed-off-by: Linkun Chen <github@lkchen.net >
2025-03-06 08:58:41 +00:00
lkchen
b3cf368d79
[V1][Molmo] Fix get_multimodal_embeddings() in molmo.py ( #14161 )
2025-03-04 15:43:59 +00:00
Harry Mellor
cdc1fa12eb
Remove unused kwargs from model definitions ( #13555 )
2025-02-24 17:13:52 -08:00
Cyrus Leung
377d10bd14
[VLM][Bugfix] Pass processor kwargs properly on init ( #13516 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-02-19 13:13:50 +00:00
Alex Brooks
983a40a8bb
[Bugfix] Fix Positive Feature Layers in Llava Models ( #13514 )
...
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com >
2025-02-19 08:50:07 +00:00
Patrick von Platen and mgoin
d366ccc4e3
[RFC] [Mistral] FP8 format ( #10130 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: mgoin <mgoin64@gmail.com >
2025-02-08 14:12:53 -07:00
Russell Bryant
e489ad7a21
[Misc] Add SPDX-License-Identifier headers to python source files ( #12628 )
...
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com >
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com >
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com >
2025-02-02 11:58:18 -08:00
Cyrus Leung
ca47e176af
[Misc] Move some model utils into vision file ( #11848 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-01-08 17:04:46 +00:00
Cyrus Leung
91445c7bc8
[Bugfix] Fix image input for Pixtral-HF ( #11741 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-01-08 10:17:16 +08:00
Cyrus Leung
eed11ebee9
[VLM] Merged multi-modal processors for LLaVA-NeXT-Video and LLaVA-OneVision ( #11717 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-01-04 11:40:53 +00:00
Cyrus Leung
8c38ee7007
[VLM] Merged multi-modal processor for LLaVA-NeXT ( #11682 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-01-02 16:39:27 +00:00
e7c7c5e822
[V1][VLM] V1 support for selected single-image models. ( #11632 )
...
Signed-off-by: Roger Wang <ywang@roblox.com >
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
Signed-off-by: Isotr0py <2037008807@qq.com >
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk >
Co-authored-by: Isotr0py <2037008807@qq.com >
2024-12-31 21:17:22 +00:00
Roger Wang
b7dcc003dc
[Model] Remove hardcoded image tokens ids from Pixtral ( #11582 )
...
Signed-off-by: Roger Wang <ywang@roblox.com >
2024-12-28 10:54:23 +00:00
Roger Wang and ywang96
c2d1b075ba
[Bugfix] Fix issues for Pixtral-Large-Instruct-2411 ( #11393 )
...
Signed-off-by: ywang96 <ywang@example.com >
Co-authored-by: ywang96 <ywang@example.com >
2024-12-21 10:15:03 +00:00
Cyrus Leung
a0f7d53beb
[Bugfix] Cleanup Pixtral HF code ( #11333 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2024-12-19 13:22:00 +00:00
Roger Wang and ywang96
59c9b6ebeb
[V1][VLM] Proper memory profiling for image language models ( #11210 )
...
Signed-off-by: Roger Wang <ywang@roblox.com >
Co-authored-by: ywang96 <ywang@example.com >
2024-12-16 22:10:57 -08:00
Cyrus Leung
93abf23a64
[VLM] Fully dynamic prompt replacement in merged input processor ( #11199 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2024-12-14 17:52:18 +00:00
Patrick von Platen
bc192a2b09
[Pixtral] Improve loading ( #11040 )
2024-12-10 06:09:32 +00:00
Roger Wang
a11f326528
[V1] Initial support of multimodal models for V1 re-arch ( #10699 )
...
Signed-off-by: Roger Wang <ywang@roblox.com >
2024-12-08 12:50:51 +00:00
Cyrus Leung
133707123e
[Model] Replace embedding models with pooling adapter ( #10769 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2024-12-01 08:02:54 +08:00
Roger Wang
9e0a147d50
[V1] Update interface for mistral-format Pixtral ( #10703 )
...
Signed-off-by: Roger Wang <ywang@roblox.com >
2024-11-27 12:26:27 +00:00
Alex Brooks and Cyrus Leung
1cfde82ffd
[Model] Add Support for Multimodal Granite Models ( #10291 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
2024-11-21 10:46:20 +00:00
Patrick von Platen
11fd7ea639
[Pixtral-Large] Pixtral actually has no bias in vision-lang adapter ( #10449 )
2024-11-19 17:33:06 +00:00
Michael Goin
281cc4b3cd
[Model][Bugfix] Support TP for PixtralHF ViT ( #10405 )
...
Signed-off-by: mgoin <michael@neuralmagic.com >
2024-11-18 10:04:14 -08:00
lkchen
c7dec926f6
[VLM] Report multi_modal_placeholders in output ( #10407 )
...
Signed-off-by: Linkun Chen <lkchen+anyscale@github.com >
2024-11-18 16:06:16 +08:00