Merged
Conversation
Contributor
Author
|
One fun thing about this model: it may not emit a |
ggerganov
approved these changes
Dec 16, 2025
Member
ggerganov
left a comment
ggerganov
left a comment
There was a problem hiding this comment.
Did a few tests with llama-server and it works as expected. Thanks!
danbev
approved these changes
Dec 16, 2025
Contributor
Author
|
Just had to remove a lingering debug line. I can merge once the tests pass, if that's OK. |
Anico2
added a commit
to Anico2/llama.cpp
that referenced
this pull request
Jan 15, 2026
* common : expose json-schema functionality to extract type info * common : fix peg parser negation during needs_more_input * common : add some defensive measures in constructed peg parser * common : add nemotron nano 3 support * common : add nemotron nano 3 tests * remove debug line
blime4
referenced
this pull request
in blime4/llama.cpp
Feb 5, 2026
* common : expose json-schema functionality to extract type info * common : fix peg parser negation during needs_more_input * common : add some defensive measures in constructed peg parser * common : add nemotron nano 3 support * common : add nemotron nano 3 tests * remove debug line
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add reasoning, response format, and tool call parsing for NVIDIA Nemotron 3 Nano (#18058)
Additional Changes
These models selectively output JSON, it is pretty much the Qwen3-Coder format. To handle schemas a bit better, I had to expose parts of the schema converter in
json-schema-to-grammarto check if a parameter resolves to a string. If it does, then always parse it as a string to keep things simple.