arXiv AI
Aug 6
Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms
arXiv:2608. 04074v1 Announce Type: cross Abstract: Long-context LLM decoding reads the key-value (KV) cache at every step.
KV Cache Compression Through the Lens of Transform Coding
arXiv:2608. 14191v1 Announce Type: new Abstract: The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference.
Related stories
arXiv AI
Jul 24
Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches
arXiv:2607. 20538v1 Announce Type: cross Abstract: Long-context Transformer inference increasingly relies on KV-cache compression or quantization.
arXiv Machine Learning
4d ago
WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms
arXiv:2609.38121v1 Announce Type: new Abstract: KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck,...
arXiv AI
Sep 17
HyQuant: Hybrid-Precision Quantization for LLM Attention
HyQuant introduces a hybrid-precision quantization framework for large language model (LLM) attention modules. It quantizes most attention states to low-bit formats while preserving a small set of vertical‑line tokens and local‑window states in full precision, guided by lightweight attention‑pattern signals. This design achieves near‑lossless accuracy across tasks while improving memory and hardware efficiency.
arXiv AI
Jul 16
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
arXiv:2505. 18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache.
arXiv Machine Learning
4d ago
QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching
arXiv:2609.36760v1 Announce Type: new Abstract: Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoupled RoPE paths, yet cache memor...
arXiv Machine Learning
Sep 15
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
arXiv:2609.13285v1 Announce Type: cross Abstract: The KV cache is a primary bottleneck for Transformer decoding: its memory footprint and cache-read traffic grow with sequence length. Grouped-query a...
arXiv Machine Learning
Jul 3
The risk of KV cache compression
arXiv:2607. 01520v1 Announce Type: new Abstract: Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache.
arXiv AI
3d ago
ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference
arXiv:2602.08005v2 Announce Type: replace-cross Abstract: Efficient long-context inference faces two coupled bottlenecks: KV-cache memory grows linearly with context length, while attention computati...
arXiv Machine Learning
Jul 1
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference
arXiv:2606. 31519v1 Announce Type: new Abstract: Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased.
arXiv AI
Jul 8
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference
arXiv:2607. 06519v1 Announce Type: new Abstract: Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning.
arXiv Machine Learning
Sep 15
Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference
arXiv:2609.13205v1 Announce Type: cross Abstract: Sparse long-context inference requires efficient token retrieval in both prefill and decode. Existing methods often use different retrieval strategie...