storyiconandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 6aa057c9d7 [Multimodal] Support custom video metadata for pre-extracted frame sequences (#40133) ...

Signed-off-by: storyicon <storyicon@foxmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-04-22 15:50:04 +08:00

..

media

[Multimodal] Support custom video metadata for pre-extracted frame sequences (#40133)

2026-04-22 15:50:04 +08:00

processing

[Model] Use helper function to run MM processors with token inputs (where applicable) (#38018)

2026-03-26 16:44:04 +08:00

__init__.py

[Misc] Reorganize inputs (#35182)

2026-03-25 10:22:54 -07:00

audio.py

[Refactor] Remove resampy dependency (#39524)

2026-04-16 08:48:17 -07:00

cache.py

[Multimodal] Simplify MM input definitions (#33331)

2026-01-29 13:32:04 +00:00

encoder_budget.py

[bug] Make sure get_modality_with_max_tokens is deterministic (#34533)

2026-02-13 20:02:59 -08:00

evs.py

[Bugfix] Fix EVS implementation for Qwen3 VL (#33607)

2026-03-04 02:18:11 +00:00

hasher.py

[Bugfix] Make MM batching more robust (#33817)

2026-02-05 20:40:58 +00:00

image.py

[3/N] Group together media-related code (#32406)

2026-01-15 11:52:12 +00:00

inputs.py

[Core] Reduce mm scheduler, get_num_embed overhead (#40143)

2026-04-18 11:25:49 +08:00

parse.py

[Misc] Reorganize inputs (#35182)

2026-03-25 10:22:54 -07:00

registry.py

[MM][CG] Optimize default max_frames_per_batch auto-infer for ViT CUDA graph video inference (#40445)

2026-04-21 14:47:53 +00:00

utils.py

[Misc] Reorganize inputs (#35182)

2026-03-25 10:22:54 -07:00

video.py

[Multimodal] Add PyAV video backend for concurrent video decoding (#39986)

2026-04-21 20:14:57 -07:00