Eagle3 triage
Skill NVIDIA/Model-Optimizer/plugins/modelopt/skills/eagle3-triage
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.From the repository description
npx -y skills add NVIDIA/Model-Optimizer --skill eagle3-triageAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.