cs.LGNov 7, 2026

CALFA-KV: Joint Calibration and Fisher-Guided Anchors for 1-Bit KV Cache Compression

Authors: Xiancai Tian, Leichao Zhang, Shenhui Zhang, Yi Shan, Hailong Li, Feng Lin, Xiaotian Yu, Aijun Li

Organizations: Shenzhen Intellifusion Technologies Co. Ltd., Shenzhen, China

Abstract

1-bit key-value (KV) cache compression can combine quantizer calibration with selective high-precision storage to reduce reconstruction error. We propose Calibration and Fisher-guided Anchors for KV cache compression (CALFA-KV). Offline, we jointly fit a key center, radial normalization parameters, and K/V vector codebooks to match the frozen model's projected attention output. We also estimate channel-wise Fisher-type sensitivities from squared gradients of a reference next-token cross-entropy loss. Online, we use these sensitivities to weight the squared reconstruction errors of each KV state. Here, a KV state is one token's key-value pair within one layer and KV head. We retain the highest-scoring states at high precision under a per-layer, per-KV-head budget. Under exact restoration, we bound the excess risk of score-based anchor selection relative to the optimum at the same anchor budget, where risk is the conditional mean square of the first-order loss change. With a budget of 56 additional FP16 anchors per layer and KV head, CALFA-KV (d8b8) outperforms all evaluated nominal 1-bit baselines on the mean score across seven benchmarks for each of the three models. At the same anchor budget, CALFA-KV (d8b10) uses a nominal index rate of 1.25 bits per channel and narrows the gap to BF16 to 0.90--2.01 points on the same metric.

Figures & tables

Explore similar work

Sep 21, 2026

KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation

What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across attention heads. Existing methods apply rank and bit-width uniformly, ignoring that each head has a different optimal mix of rank truncation and quantization. We show that co-optimizing rank and bit-width per head, using only standard low-rank projection and scalar quantization, dominates uniform allocation, with the largest gains at low bit-rates. Our method, KV-COBRA (Co-Optimized Bit-Rank Allocation), formalizes this as a resource-allocation problem: it balances rank-truncation loss against quantization loss within each head, then redistributes budget across heads to minimize total distortion. A fused Hadamard rotation equalizes per-channel variance, and reordering the SVD basis by attention-KL importance makes the solver query-aware. The same allocator extends to joint K+VK{+}V compression. On perplexity, zero-shot, and long-context benchmarks from 0.50.5 to 44 bits per dimension (bpd), KV-COBRA shows the smallest accuracy degradation among evaluated methods at low bpd, with no per-token overhead.
Aug 3, 2026

AnchorKV: Anchor-Residual KV Cache Compression

The key-value (KV) cache is the primary memory bottleneck in long-context LLM inference. Existing approaches attack it from opposite ends: eviction methods permanently discard tokens, degrading performance whenever a discarded token later proves essential, while quantization methods retain all tokens at low precision but offer limited compression. We propose AnchorKV, a compression scheme that shrinks the cache by 20×20\times without discarding a single token. AnchorKV represents the cache using a small set of anchors stored exactly, expresses every other token through its most similar anchor, and refines only those whose approximation most affects the model's output. AnchorKV consistently preserves accuracy across models and datasets, retaining 99% of the full-cache score at the 70B scale, while keeping the entire context at a fraction of its cost.
Oct 2, 2026

Tailoring the Quantization Space for 1-Bit KV Cache Compression

The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwidth. To mitigate this bottleneck, vector quantization (VQ) has emerged as a promising approach for aggressive KV cache compression. However, existing VQ methods degrade substantially in the 1-bit regime. At such extreme compression, each codebook must represent a larger group of channels with a limited set of centroids, making effective use of its capacity increasingly challenging. To address this, we introduce TaSQ\textbf{TaSQ}, which tailors the VQ target space by combining query-guided channel weighting, cross-head normalization, and covariance-aware channel grouping to better reflect the error sensitivity and statistical structure of cached activations. Since these transforms are RoPE-compatible and can be easily merged into projection weights and codebooks, TaSQ preserves the conventional VQ lookup structure and adds negligible serving overhead. Across general, long-chain-of-thought reasoning, and long-context retrieval benchmarks, TaSQ consistently outperforms existing low-bit KV cache VQ baselines while preserving reasoning stability. On a single RTX 6000 Ada GPU, its SGLang implementation supports up to 14×14\times larger batch sizes and achieves 1.87×1.87\times higher peak throughput compared to the BF16 baseline.