A collection of notebooks demonstrating deployment and fine-tuning cookbooks for NVIDIA Nemotron-3-Super.
These notebooks provide end-to-end recipes for deploying and customizing Nemotron-3-Super.
- vllm_cookbook.ipynb — Deploy Nemotron-3-Super with vLLM.
- sglang_cookbook.ipynb — Deploy Nemotron-3-Super with SGLang.
- trtllm_cookbook.ipynb — Deploy Nemotron-3-Super with TensorRT-LLM.
- SparkDeploymentGuide — DGX Spark single-GPU deployment guide for Nemotron 3 Super with vLLM (nightly) and TensorRT-LLM, including NVFP4 quantization and MTP speculative decoding.
- grpo-dapo — Full-weight RL training with GRPO/DAPO algorithm, reproducing emergent math reasoning from a base model.
- lora-text2sql — Supervised fine-tuning (LoRA) recipe for the Text2SQL use case, including dataset preparation and training with NeMo Megatron-Bridge and NeMo AutoModel libraries.
- OpenScaffoldingResources — Guides for using Nemotron-3-Super with agentic coding tools (OpenCode, OpenClaw, Kilo Code CLI, OpenHands) via OpenRouter and build.nvidia.com.