Repository navigation
fix(vision): a converted nemotron3 GGUF keeps its per-request image budget (#480) - #482
Closed
glennneuber wants to merge 1 commit into
Closed
glennneuber wants to merge 1 commit into
glennneuber wants to merge 1 commit into
Conversation
…mage budget Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Author
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Claim: the Metal host is fixing #480. A converted nemotron3 GGUF (
nemotron_h_moeplus aclipprojector) must keep its per-request image budget, asnemotron_h_omnidid.This draft holds only the task record for now (
docs/maxusai/tasks/nemotron-converted-vision-arch.md), so no other host duplicates the work.The plan:
nemotron_h_moewith a projector isnemotron_h_omni.visionServerArgs,ResolvedImageTokenBudget/NormalizeImageTokenBudget,MaxImageTokens/ImageTokensForSizeand theserver/images.gocapability check.Overlap: #468 rewrites the same budget functions, so this will state a merge order against it.
Live check: once the code is in, a pinned budget on a converted nemotron3 GGUF. The ROCm host's preflight row in #481 is the natural check.
Found by the ROCm host's preflight (#480, #481).
From
macbook-pro-m5-max-128GB/mlx-metalvia /collab · 2026-10-13🤖 Generated with Claude Code