2 papers
cs.LG2026
Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter
Pier-Jean Malandrino
Leech-lattice quantization gives good quality at two bits per weight, but its codebooks hold more than 10^14 points, too many for a lookup table. Our earlier kernel expanded the co…
cs.LG2026
Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights
Pier-Jean Malandrino
Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluation protocol. Its kernel decodes one shell; we found no implementation of the mult…