cuopt-agent: update reasoning LLM to minimaxai/minimax-m3#158
Open
cafzal wants to merge 1 commit into
Open
Conversation
Signed-off-by: cafzal <cameron.afzal@gmail.com>
Contributor
Author
|
@rgsl888prabhu quick config fix: agent reasoning model m2.5 → m3 (m2.5 deprecated so fresh clones can't run on build.nvidia.com NIM inference endpoints). Ready for review. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Updates the cuopt-agent's reasoning LLM from
minimaxai/minimax-m2.5tominimaxai/minimax-m3in both configs (config-deepagent.yml,config-deepagent-eval.yml) and the README model table.Why
minimaxai/minimax-m2.5has been deprecated on theintegrate.api.nvidia.comNIM endpoint the agent points at by default, so the shipped config no longer runs against it.minimaxai/minimax-m3is the current MiniMax model there — confirmed working in a live call (it produced the expected multi-objective reasoning and its solve grounded correctly on cuOpt). This restores a fresh clone's ability to run against the default endpoint.