Running on Zero Agents Featured 267 Laya Demo 🎯 267 Fast System 1 decisions with calibrated probabilities
Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights Paper • 2609.02652 • Published Sep 2
view article Article I put a 24 dimensional lattice in a CUDA kernel to run Qwen3-4B in 2.6 GB Pier-Jean • Aug 29