eagle3-new-model
OfficialConfigure new EAGLE3 model pipelines faster
AuthorNVIDIA
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps users configure new EAGLE3 model checkpoints for offline pipeline execution without manually designing launcher YAML files or selecting incompatible settings.
Core Features & Use Cases
- Launcher Configuration Guidance: Creates a new hf_offline_eagle3.yaml configuration by adapting the closest existing model example.
- Backend Selection Support: Determines whether to use vLLM, HF, or TRT-LLM hidden-state dumping based on model characteristics such as multimodal support, attention patterns, and deployment compatibility.
- Model-Specific Adjustments: Handles configuration details including trust-remote-code requirements, MoE expert dimensions, and tokenizer environment settings for new checkpoints.
Quick Start
Ask the skill to configure an EAGLE3 offline pipeline YAML for a new model checkpoint by selecting the correct backend and adapting an existing example.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: eagle3-new-model Download link: https://github.com/NVIDIA/Model-Optimizer/archive/main.zip#eagle3-new-model Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 545,000+ vetted skills library on demand.