[Runtime] Add NVIDIA-Nemotron-3-Super-120B-A12B-FP8 runtime#610
Open
TJ5 wants to merge 4 commits into
Open
Conversation
github-actions
Bot
added
runtime
TJ5
requested review from
CatherineSue,
XinyueZhang369 and
slin1237
as code owners
This reverts commit 0f5d64e.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this PR does
Adds OME configuration for serving NVIDIA Nemotron 3 Super 120B A12B FP8 with a 1M context window:
Adds the
nvidia-nemotron-3-super-120b-a12b-fp8ClusterBaseModelpointing tohf://nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8.Adds the
vllm-nvidia-nemotron-3-super-120b-a12b-fp8ClusterServingRuntimewith SMG router + vLLM settings for NemotronHForCausalLM, FP8 KV cache, 4-way tensor parallelism, H100 scheduling, chunked prefill, Nemotron v3 reasoning parsing, and Qwen3 Coder tool-call parsing.Registers the model and runtime in the kustomizations.
Adds a sample
InferenceServicefor the NVIDIA Nemotron namespace.Why we need it
Enables serving for NVIDIA-Nemotron-3-Super-120B-A12B-FP8.
Fixes #
How to test
Checklist
make testpasses locally