Cyrus LeungandQwen Code ebcd606467 [MM] Simplify prompt updates: replace PromptSeq with list[int] (#53372) ...

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Qwen Code <noreply@alibaba-inc.com>

2026-08-23 14:50:32 +08:00

..

media

Fix DoS via sample-rate forgery bypassing audio decode duration guard (#49948)

2026-08-10 15:49:17 +00:00

processing

[MM] Simplify prompt updates: replace PromptSeq with list[int] (#53372)

2026-08-23 14:50:32 +08:00

video_decoders

[Bugfix] Video loading: sample over presentable frames, not header sample count (MP4 edit-list trims) (#48608)

2026-08-20 04:23:09 +00:00

video_prune

[Feature] Add VidCom2 video token pruning (#47750)

2026-07-28 03:20:17 +00:00

__init__.py

[Misc] Reorganize inputs (#35182)

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

audio.py

[Misc] Clarify mono audio requirement (#50141)

2026-07-31 10:46:53 +00:00

cache.py

[Bugfix] Skip MM processor cache inserts larger than capacity (#53016)

2026-08-20 13:42:50 +00:00

encoder_budget.py

[MRV2] Add encoder cache profiling implementation (#47985)

2026-07-20 20:18:14 -07:00

gpu_ipc_memory.py

[Multimodal] Reorganize video decoder backends (#49155)

2026-08-18 15:06:18 +00:00

hasher.py

[Multimodal] Expose mm hash algothrim selection to cli args (#49686)

2026-07-31 05:25:19 +00:00

image.py

[Security] Fix image EXIF orientation and tRNS transparency handling (#44974)

2026-06-09 09:34:44 -07:00

inputs.py

[EPD] Remove duplicate image preprocessing in EPD and enable preprocess on GPU (#50390)

2026-08-05 15:59:54 -07:00

parse.py

[EPD] Allow KV consumers to omit MM embeddings (#52697)

2026-08-19 02:16:08 +00:00

registry.py

[Bugfix][Model] Fix Qwen3.5 MTP for text-only checkpoints (#50734)

2026-08-10 11:04:53 +00:00

utils.py

[Core] Skip broadcasting mm tensor data to workers for prefix-cache-covered items (#52041)

2026-08-19 07:16:39 -07:00

video.py

[CI] Fix docs build (#52937)

2026-08-19 05:25:46 -07:00