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

..

assets

Re-submit: Fix: Proper RGBA -> RGB conversion for PIL images. (#18569)

2025-05-23 01:59:18 +00:00

__init__.py

[Core] Support image processor (#4197)

2024-06-02 22:56:41 -07:00

test_cache.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

test_hasher.py

Improve multimodal hasher performance for re-used Image prompts (#22825)

2025-08-15 12:32:56 +00:00

test_image.py

feat(multimodal): Add customizable background color for RGBA to RGB conversion (#22052)

2025-08-01 06:07:33 -07:00

test_inputs.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_processing.py

[Core] Store only the keys for multi-modal data in P0 (#22198)

2025-08-07 01:45:04 -07:00

test_registry.py

Implicit language-model-only mode via limit-mm-per-prompt (#22299)

2025-08-08 22:21:40 -07:00

test_utils.py

[FEAT] [Performance] Enable DP for ViT in Qwen2.5VL (#22742)

2025-08-19 15:25:57 +00:00

test_video.py

[Bugfix] Fix ndarray video color from VideoAsset (#21064)

2025-07-19 02:17:16 -07:00

utils.py

[Bugfix] Fix ndarray video color from VideoAsset (#21064)

2025-07-19 02:17:16 -07:00