Research questionHow can multi-shell Leech-lattice 2-bit weights be decoded efficiently for batch-one GPU serving?Multi-shell Leech-lattice weights require decoding more than one codebook shell during inference. Their GPU representation affects memory traffic and latency, while the aggressive quantization can reduce model quality. Latest papersRecent research connected to this question, newest first.Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM WeightsThe evidence covers decode-phase GEMV at batch size 1 using the full 301-class codebook, with offline-expanded GPU layouts and fused dequantization with matrix-vector multiplication. It reports bit-exact VRAM layout measurements, comparisons with FP16, AWQ, and QTIP kernels, results across two memory hierarchies, and end-to-end measurements for 4B, 8B, and 14B models alongside perplexity and MMLU quality results.research paper · Sep 2, 2026