RAQ-MLA introduces a role-aware quantization scheme for Multi-Head Latent Attention (MLA) caches used in large language models. It analyzes the distinct functions of the cached latent and positional key tensors, applying tailored invertible transforms to each based on their impact on attention output. The method achieves near-lossless performance while reducing the cache size to about 2.5 bits per element, effectively increasing theoretical KV-cache capacity by 6.5×.
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:2608. 02691v1 Announce Type: cross Abstract: The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important.
RoLaQ is an offline technique that jointly calibrates rotation and quantization range for 2‑bit key‑value caches in multi‑head latent attention models. By refining a shared rotation within subspaces defined by frozen key and value projections and learning coupled quantization thresholds and reconstruction gains, RoLaQ improves prediction matching and attention‑output supervision while keeping model weights frozen. Experiments on three MLA models and six benchmarks show that RoLaQ outperforms other 2‑bit methods, achieving higher average accuracy and, in a DeepSeek‑V2‑Lite implementation, nearly four times the BF16 KV capacity and more than double the decode throughput for 256K input tokens.
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free r...
The paper introduces JoLT, a training‑free compressor that jointly allocates rank and precision for key‑value (KV) cache compression in long‑context language models. JoLT treats grouped prefill caches as fourth‑order tensors, applies partial Tucker decomposition along token and feature modes, and uses a rotated low‑bit quantizer for residuals, all governed by a single Lagrangian dual under a global byte constraint. Across five models from four architecture families, JoLT achieves 2–3× compression with less than 0.2% perplexity loss, and near‑lossless retrieval accuracy on LLaMA‑3.1‑8B at 64K context up to 3× compression.
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:2607. 24331v1 Announce Type: new Abstract: As the inference phase of Large Language Models (LLMs) requires handling long context windows, the Key-Value (KV) cache initially appears to address this challenge but eventually becomes a significant bottleneck as the context window continues to grow.
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
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:2604.11501v2 Announce Type: replace-cross Abstract: Rank reduction discards dimensions; quantization keeps them at lower precision. Comparing the two requires a choice of what compression shoul...
arXiv:2607. 23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference.
arXiv:2606. 16310v1 Announce Type: new Abstract: Query-key (QK) normalization stabilizes attention by controlling the scale of queries and keys before the dot product, but is not immediately compatible with Multi-head Latent Attention (MLA).