sglang-nemotron-super-optimization

Community

PR-backed optimization for Nemotron Super.

AuthorBBuf
Version1.0.0
Installs0

System Documentation

What problem does it solve?

PR-backed optimization manual provides canonical guidance to audit, extend, and document Nemotron Super and Nano Hybrid optimizations within SGLang, ensuring diffs are production-ready and evidence-backed.

Core Features & Use Cases

  • PR-diff dossier-guided optimization for Nemotron Super family, including NemotronH, Nemotron Nano VL, NVFP4, and MoE variants.
  • Evidence-driven validation with runtime surface mappings and change-history references to ensure traceability across PRs.
  • Use cases include auditing model changes, extending hybrid architectures, and validating performance and safety improvements in CI pipelines.

Quick Start

Begin by reviewing the non-negotiable evidence rule and the PR history reference in references/pr-history.md to start applying the canonical Nemotron optimization patterns.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: sglang-nemotron-super-optimization
Download link: https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/archive/main.zip#sglang-nemotron-super-optimization

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.