High-performance LLM inference optimization framework for NVIDIA GPUs with Python API
Autonomous experiment loops for AI coding agents - try ideas, measure results, keep what works
High-performance generative AI inference library for PC and laptop deployment with optimized resource consumption
Lightning-fast LLM inference engine built from scratch in 1,200 lines of Python
AI-first search optimization skill for Claude Code — citability scoring, crawler analysis, and GEO audits
NVIDIA's high-performance deep learning inference SDK for GPU-accelerated AI deployment
