← All skills

speculative-decoding

80 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By NVIDIA/Model-Optimizer (GitHub) · coding · 5,579 stars · scanned at commit 6713c5a

Train, debug, and validate a speculative decoding draft model (EAGLE3, DFlash, DSpark, Domino) through the ModelOpt launcher pipeline. Use when the user wants to add a new model to a draft-training pipeline, asks why a pipeline run failed, wants experiment logs reviewed, or wants to check whether a run's acceptance rate meets threshold. Triggers on "EAGLE3", "DFlash", "DSpark", "Domino", "draft model", "acceptance rate", "speculative decoding pipeline". Do NOT use for quantizing a model (use pt…

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'speculative-decoding' ] || [ -L ~/.agents/skills/'speculative-decoding' ]; then echo 'A skill folder named speculative-decoding already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/Model-Optimizer' "$d" && git -C "$d" checkout --quiet '6713c5a679fab80fdd9b688df01845f545c307b1' -- 'plugins/modelopt/skills/speculative-decoding' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/modelopt/skills/speculative-decoding' ~/.agents/skills/'speculative-decoding' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'speculative-decoding' ~/.claude/skills/'speculative-decoding' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for NVIDIA/Model-Optimizer shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/NVIDIA/Model-Optimizer.svg)](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/Model-Optimizer/)

Score history