llmc

AI & ML interests

LLM training in simple, pure C/CUDA

Recent Activity

Elixpo  submitted a paper about 3 hours ago

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

Elixpo  authored a paper about 11 hours ago

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

eliebak  authored a paper 16 days ago

Prime Agent: A Self-Improving RLM Harness

View all activity

Team members 36