Auto-Inference-Optimiser
github.com/manthanguptaa/auto-inference-optimiser- Category
- AI Agents
- Pricing
- Open Source
- Type
- TOOL
- Builder
- manthanguptaa
- GitHub
- 38 stars
- Added
- Apr 15, 2026
About
An autonomous AI agent that automatically optimizes LLM inference speed on Apple Silicon by running experiments overnight. It hill-climbs on tokens per second by modifying inference code and uses git commits as experiment tracking.
Why it made the leaderboard
An agent that spends the night making LLM inference faster on your Apple Silicon machine — hill-climbing tokens-per-second by editing inference code, with git commits as the experiment log. The author reports a 10.7% speedup with quality safeguards; inspired by karpathy's autoresearch.
Tags
llmoptimizationinferenceapple-siliconautomationperformancemlx
Tech Stack
Python
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.