Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights

• URL: http://arxiv.org/abs/2609.02652v1
• Date: Wed, 02 Sep 2026 14:26:06 GMT
• Title: Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights
• Abstract summary: Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluation protocol.<n>This paper supplies one and measures its serving cost for decode-phase GEMV at batch 1.
• Score: 8.550323073861415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 multi-shell decoder the rate requires. This paper supplies one and measures its serving cost for decode-phase GEMV at batch 1. First, a serving path for the full 301-class codebook: an offline expansion into GPU layouts and a fused dequantize-plus-matvec kernel reading them without warp divergence, verified against f64. Second, the in-VRAM rate is a design axis distinct from the on-disk rate. Four bit-exact layouts timed in one process show binary bit planes beating one-hot masks on size and speed at constant bandwidth (4.80 bits per weight, 2.15x FP16). Below 4.3 bits a second, irregular stream enters; at 3.6 the decode stops being shifts and masks. Third, deployed four-bit (AWQ) and two-bit (QTIP) GEMV kernels run in the same process. The trellis kernel reads 2.40x fewer bytes than our served layout and runs 2.27x faster at near-equal fractions of their byte bounds: the time gap tracks the traffic gap, the price of unfolding a codebook too large for a lookup table. Fourth, the validity envelope: the trellis kernel outruns our no-weights control, so our launch geometry sets that floor, and on a second memory hierarchy every lattice arm falls below FP16. With the output head held identical across arms, the kernel-and-format path gains 1.11x, 1.29x and 1.41x end to end at 4B, 8B and 14B; with an int8 output head the served 4B reaches 87.0 tok/s in 2.60 GB. The quality cost, 1.38x perplexity and 14.7 MMLU points at 4B, shrinks across the three sizes measured.

Related papers

• VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention [47.30761996669105]
  We propose VC-Attention, a training-free low-bit attention framework.<n>It addresses both by smoothing value tokens by a probability Cast. V-Smooth reorders value tokens by lightweight clustering online, so the tokens in a fused hardware block quantize well together.<n>It maps log-domain scores directly to E4M3 probability codes with one fused multiply-add, eliminating the FP32 exponential and the format conversion.
  arXiv  Detail & Related papers  (2026-09-14T16:17:35Z)
• Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving [0.28304882054363123]
  This work is the first to impose that identity as a constraint inside PTQTP's solver.<n>We apply this to the routed experts of DeepSeek-V4-Flash-0731, a 284B-A13B mixture-of-experts model.<n>All code, formats, and evaluation artifacts are open source in the fucina inference stack.
  arXiv  Detail & Related papers  (2026-08-09T20:53:47Z)
• A Modern Multimodal Assistant on a 6 GB 2011 GPU: Stage-Validated, All-GPU CUDA Inference for Fermi [0.0]
  This report keeps the hardware and asks what a model that fits can do.<n>We deploy Mini-V-4.6, a modern multimodal assistant pairing a SigLIP2 encoder and window-attention merger.<n>The system answers an image question end-to-end in 1.7s.
  arXiv  Detail & Related papers  (2026-07-16T04:48:44Z)
• Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models [0.0]
  We introduce Variable Bit-width Quantization (VBQ)<n>Training-time method in which each contiguous group of 64 weights learns its own resolution from 1,2,4,8 bits.<n>As quality-per-byte, VBQ is 3.9-8.4x more efficient than FP16.
  arXiv  Detail & Related papers  (2026-07-03T02:42:04Z)
• RoPE-Aware Bit Allocation for KV-Cache Quantization [52.099459337231345]
  Block-GTQ is a bit allocator for key-cache quantization built on TurboQuant-MSE.<n>It better preserves RoPE query-key logits on a ten-model diagnostic panel.<n>It runs 1.34x faster than fp16 FlashAttention2 at 128K context.
  arXiv  Detail & Related papers  (2026-06-23T00:17:48Z)
• XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference [0.0]
  XFP determines codebook size, outlier budget, and packing per layer automatically.<n>XFP reaches 138 tok/s single-stream decode on workstation hardware.<n>For models that do not fit in the target memory envelope, we present the H-Process.
  arXiv  Detail & Related papers  (2026-05-14T13:52:31Z)
• Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels [83.99688944263843]
  Weight-De Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction.<n>At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16.<n>A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r2) intermediates, eliminating the dense product.
  arXiv  Detail & Related papers  (2026-03-23T17:57:24Z)
• A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA [10.452946241750562]
  Gated DeltaNet (GDN) is a linear attention mechanism that replaces the growing KV cache with a fixed-size recurrent state.<n>We show that this bottleneck is architectural, not algorithmic, as all subquadratic sequence models exhibit arithmetic intensities below 1 FLOP/B at decode time.<n>We present an FPGA accelerator that eliminates this bottleneck by holding the full 2 MB recurrent state persistently in on-chip BRAM.
  arXiv  Detail & Related papers  (2026-03-06T06:03:38Z)
• CommVQ: Commutative Vector Quantization for KV Cache Compression [50.37946553931796]
  We propose Commutative Vector Quantization (CommVQ) to significantly reduce memory usage for long-context LLM inference.<n>We first introduce additive quantization with a lightweight encoder and codebook to compress the KV cache.<n>Our approach achieves high accuracy with additive quantization and low overhead via the RoPE-commutative codebook.
  arXiv  Detail & Related papers  (2025-06-23T17:50:11Z)
• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models [61.474101404805545]
  Diffusion models can generate high-quality images, but as they scale, rising memory demands and higher latency pose deployment challenges.<n>We propose SVDQuant, a new 4-bit quantization paradigm to overcome this limitation.<n>We reduce the memory usage for the 12B FLUX.1 models by 3.5$times$, achieving 3.0$times$ speedup over the 4-bit weight-only quantization (W4A16) baseline.
  arXiv  Detail & Related papers  (2024-11-07T18:59:58Z)
• DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training [82.06732962485754]
  FlashAttention effectively reduces the quadratic peak memory usage to linear in training transformer-based large language models (LLMs) on a single GPU. We introduce DISTFLASHATTN, a memory-efficient attention mechanism optimized for long-context LLMs training. It achieves 1.67x and 1.26 - 1.88x speedup compared to recent Ring Attention and DeepSpeed-Ulysses.
  arXiv  Detail & Related papers  (2023-10-05T03:47:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.