# VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference

arXiv: https://arxiv.org/abs/2503.02236 · HTML: https://mlsanity.com/paper/2503.02236/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2025.

## Built on by (most cited first, 13 of 13)

- [M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization](https://mlsanity.com/paper/2601.19213/) (2026)
- [Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs](https://mlsanity.com/paper/2602.05191/) (2026)
- [VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization](https://mlsanity.com/paper/2510.06175/) (2025)
- [Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding](https://mlsanity.com/paper/2512.23858/) (2025)
- [Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization](https://mlsanity.com/paper/2607.08057/) (2026)
- [Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning](https://mlsanity.com/paper/2508.06588/) (2025)
- [CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels](https://mlsanity.com/paper/2605.05023/) (2026)
- [EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture](https://mlsanity.com/paper/2605.24144/) (2026)
- [Hardwired-Neurons Language Processing Units as General-Purpose Cognitive Substrates](https://mlsanity.com/paper/2508.16151/) (2025)
- [ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive](https://mlsanity.com/paper/2508.18850/) (2025)
- [VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization](https://mlsanity.com/paper/2603.16435/) (2026)
- [A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference](https://mlsanity.com/paper/2607.24148/) (2026)
- [Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving](https://mlsanity.com/paper/2609.33536/) (2026)

## Abstract (arXiv)

In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cache to optimize codebook access efficiency and support the integration of VQ with various computations. The codebook cache adaptively stores different entries across the GPU's memory hierarchy, including off-chip global memory, on-chip shared memory, and registers. Centered around the codebook cache, we design an efficient computation engine that optimizes memory traffic during computations involving codebooks. This compute engine adopts the codebook-centric dataflow and fusion optimizations. Additionally, we provide adaptive heuristics to tailor parameter selection in our optimizations to diverse VQ configurations. Our optimizations achieve an average latency reduction of 46.13% compared to unoptimized versions. Compared to existing open-source implementations, our methods decrease latency by 64.36% to 99.1%. A final comparison with state-of-the-art element-wise quantization methods like AWQ and KVQuant shows that our VQ-LLM is practically viable, achieving latencies close or even better latencies to those at equivalent bit-widths, potentially offering greater accuracy.