GitHub · Python
sybil-solutions/inference-optimisation-skill
Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization
- Stars
- 1,810
- Forks
- 168
- Stars gained in 24 hours
- +292
- Forks gained in 24 hours
- +28
Topics: agent-skill, benchmarking, claude-code, inference, llm, speculative-decoding
Latest data point: Nov 22, 2026 · 1,810 stars · 168 forks