Add NVIDIA NIM provider support#185
Open
hrishinave wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #108
Adds NVIDIA NIM as a provider with 3.3 Nemotron Super 49B, plus three more
from the catalog (Nemotron 3 Ultra, GLM-5.2, DeepSeek-V4-Pro). OpenAI-compatible,
verified against the live API — key validation and an end-to-end chat turn with a
tool call.
A little note: NIM's
/v1/modelsis public. It returns 200 for any key,including an empty one, so the usual list-models probe can't tell a good key from a
typo, so auth is only enforced on inference. The verify path POSTs a 1-token completion
against the recommended model instead. Covered in
test_provider_verify.py.pytest 893 passed / 1 skipped, vitest 68, Playwright e2e 154.