feat(media): add per-target image and video processing - #804
Draft
ayushag-nv wants to merge 5 commits into
Draft
ayushag-nv wants to merge 5 commits into
ayushag-nv wants to merge 5 commits into
Conversation
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: ayushag <ayushag@nvidia.com>
|
ayushag-nv
marked this pull request as draft
September 21, 2026 15:24
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
Judge and answer endpoints need different image sizes and video representations. Builds on #790; related to SWITCH-1542.
What
Add per-target TOML media settings for image resizing/limits, video frame sampling, native video formats, and media omission. Include FFmpeg in the server image.
How
A separate
switchyard-mediacrate prepares outgoing bodies in the LLM client before retries. Downloads, decoding, and frame extraction are bounded. Original requests remain available to answer and fallback targets;libsygains no media dependencies.Where to Start Review
Start with
crates/switchyard-media/src/lib.rs, then the clientsend_encodedhook and runner configuration. The example includes Cosmos judge and Astra/Qwen/Gemini answer settings.Test Plan
prefill-router, and 2 FFmpeg tests passed.