Inference Optimisation Skill

Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization.

What you get

Inference Optimisation Skill is a free, open-source AI tool published on GitHub by sybil-solutions. Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization. GitHub stars: 692 License: MIT (free to use) Language: Python Topics: agent-skill, benchmarking, claude-code, inference, llm, speculative-decoding Last updated: 2026-11-16 How to get it: open the repository on GitHub, read the README and follow the setup steps. HEEEXY lists it in the Lab because it is popular, actively maintained and openly licensed.

More for new on github

  • Yetone Magpie: Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
  • Printfilm: PRINTFILM: AI short-video marketing and AI short-drama creation platform
  • Vercel Labs UI: A library of behaviors for agents to build the next generation of user interfaces.