Wenqi Glantz 4924ac582c

Add hidden dimension validation for multimodal embedding inputs (#30968) ...

Signed-off-by: Wenqi Glantz <wglantz@nvidia.com>

2025-12-19 07:59:36 +00:00

..

__init__.py

…

audio.py

additional protection for CVE-2025-62164 (#30649)

2025-12-15 03:07:10 +00:00

base.py

[Bugfix] Follow-up fix on MediaWithBytes (#29951)

2025-12-03 10:42:49 +00:00

cache.py

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -08:00

evs.py

…

hasher.py

[Multimodal][Core] Optimize multimodal preprocessing cache by hashing image bytes instead of pixel values (#29621)

2025-12-02 21:49:02 +08:00

image.py

additional protection for CVE-2025-62164 (#30649)

2025-12-15 03:07:10 +00:00

inputs.py

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)

2025-12-16 14:18:17 -08:00

parse.py

Add hidden dimension validation for multimodal embedding inputs (#30968)

2025-12-19 07:59:36 +00:00

processing.py

Add hidden dimension validation for multimodal embedding inputs (#30968)

2025-12-19 07:59:36 +00:00

profiling.py

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)

2025-12-16 14:18:17 -08:00

registry.py

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)

2025-12-16 14:18:17 -08:00

utils.py

[Chore] Delay recent deprecations (#30398)

2025-12-10 17:48:38 +00:00

video.py

[Fix] Update lazing loading of video loader backend (#30444)

2025-12-11 10:14:57 +00:00