Runtime-Certified Bounded-Error Quantized Attention

• URL: http://arxiv.org/abs/2605.20868v1
• Date: Wed, 20 May 2026 08:04:40 GMT
• Title: Runtime-Certified Bounded-Error Quantized Attention
• Abstract summary: We present a tiered KV cache architecture that enables runtime-certified attention.<n>A two-term error decomposition yields per-head, per-step bounds on (i) attention distribution distortion from key quantization and (ii) value reconstruction error.<n>Across PG-19, NIAH, and RULER benchmarks, the system matches dense FP16 KV quality within noise for language modelling and retrieval tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or recover from failures at runtime. We present a tiered KV cache architecture that enables runtime-certified attention: INT8 keys and INT4 values are stored in GPU memory, while FP16 originals are retained in system RAM for deterministic fallback. A two-term error decomposition yields per-head, per-step bounds on (i) attention distribution distortion from key quantization and (ii) value reconstruction error. These bounds are computed online and used to drive adaptive precision selection and a multi-stage fallback ladder, which guarantees recovery to the exact dense attention output when required. Across PG-19, NIAH, and RULER benchmarks on LLaMA~3.1-8B with contexts up to 128K, the system matches dense FP16 KV quality within noise for language modelling and retrieval tasks, while recovering catastrophic failures observed in naive INT8/INT4 baselines. Value-sensitive tasks at short context expose a controlled trade-off between compression and fidelity, which can be eliminated via tighter value tolerances or FP16-value fallback. The certification is local (per-head, per-step) and does not guarantee end-to-end model correctness, but ensures that each attention computation is either bounded relative to an FP16 reference or exactly recovered via fallback. This reframes KV cache quantization as a runtime-verified computation rather than a fixed approximation. The goal is not raw speedups, but enabling safe deployment of aggressive KV compression under strict quality constraints.

Related papers

• CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration [67.17709877327232]
  Cate KV is a hybrid KV cache method that retains only critical token information for consistent heads.<n>Cate KV reduces memory usage by up to $2.72times$ and accelerates decoding by $2.18times$ in single-sample inputs.
  arXiv  Detail & Related papers  (2026-08-31T06:02:37Z)
• DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression [0.0]
  DepthWeave-KV is a token-adaptive cache compression method that factorizes key and value states across neighboring transformer layers.<n> DepthWeave-KV achieves near-full-output task quality with substantially lower memory use.
  arXiv  Detail & Related papers  (2026-07-07T17:29:01Z)
• Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL [18.134050827462005]
  Large Language Models (LLMs) deploy into mission-critical domains (e.g. finance, medicine, law)<n>Experiments with 16-bit precisions still exhibit catastrophic output divergence across heterogeneous GPUs.<n>We propose Hybrid Error ALleviation (HEAL), a targeted intervention that approximates FP32 accelerators while resolving hardware constraints.
  arXiv  Detail & Related papers  (2026-06-19T01:21:10Z)
• Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation [6.129872931808218]
  Key-value ( KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory.<n>In this study, we explore alignment preservation under KV cache quantization.<n>We find that low-bit quantization can silently destroy safety alignment.
  arXiv  Detail & Related papers  (2026-06-01T02:02:20Z)
• OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond [50.440302567029654]
  Multi-modal intelligence has made the Key-Value cache a dominant memory bottleneck for efficient deployment.<n>In this work, we revisit the inherent limitations of the per-channel quantization paradigm.<n>We propose OScaR, an accurate and lightweight KV cache compression framework for X-LLMs.
  arXiv  Detail & Related papers  (2026-05-19T10:53:03Z)
• Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility [31.124813359673073]
  We introduce Self-Pruned Key-Value Attention (SP-KV), a mechanism designed to predict future KV utility.<n>A lightweight utility predictor scores each key-value pair, and while recent KVs are always available via a local window, older pairs are written in the cache.<n>The mechanism adapts to the input and typically reduces the KV cache size by a factor of $3$ to $10times$.
  arXiv  Detail & Related papers  (2026-05-13T18:58:16Z)
• Towards Joint Quantization and Token Pruning of Vision-Language Models [53.978753457744055]
  Token pruning and low-bit quantization are complementary for reducing inference costs.<n>We present a collaborative quantization-and-pruning framework that unifies low-bit inference and deterministic visual-token pruning.<n> Experiments on standard VLM benchmarks show improved robustness over stage-wise baselines under the same low-bit regime.
  arXiv  Detail & Related papers  (2026-04-19T08:18:29Z)
• Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs [8.332279450103151]
  Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks.<n>On-device LLM inference is heavily constrained by the memory and bandwidth overhead of the key-value (KV) cache.<n>We propose adaptive KV-cache quantization, a learned policy that assigns bit-width proportional to token importance.
  arXiv  Detail & Related papers  (2026-04-06T14:45:49Z)
• Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression [4.049313299965171]
  Motivated by this gap between compression and acceleration, we study a practical, ordered pipeline that targets measured latency.<n>We combine three widely used techniques: unstructured pruning, quantization-aware training (QAT), and knowledge distillation (KD)<n>Across all settings, the ordered pipeline achieves a stronger accuracy-size-latency frontier than any single technique alone.
  arXiv  Detail & Related papers  (2026-04-05T06:13:47Z)
• PatternKV: Flattening KV Representation Expands Quantization Headroom [37.83913102876393]
  KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference.<n> KV quantization is a key lever for reducing cache cost, but accuracy drops sharply as the native KV distribution lacks flatness.<n>We show that the K cache maintains a stable structure that evolves gradually with context, while the V cache carries latent semantic regularities.
  arXiv  Detail & Related papers  (2025-10-05T12:09:14Z)
• XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization [58.92253769255316]
  LLM inference is challenging due to substantial memory footprint and bandwidth requirements.<n>XQuant exploits the rapidly increasing compute capabilities of hardware platforms to eliminate the memory bottleneck.<n>XQuant-CL exploits the cross-layer similarity in the X embeddings for extreme compression.
  arXiv  Detail & Related papers  (2025-08-14T06:52:38Z)
• Quantize What Counts: More for Keys, Less for Values [63.51476878610841]
  Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value ( KV) cache.<n>This paper proposes two theorems that anchor mixed-precision KV quantization in the intrinsic geometry of Transformer models.
  arXiv  Detail & Related papers  (2025-02-20T22:24:27Z)
• vCache: Verified Semantic Prompt Caching [95.16654660556975]
  This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees.<n>It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training.<n>Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines.
  arXiv  Detail & Related papers  (2025-02-06T04:16:20Z)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization [31.806112535762367]
  Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models(LLMs)
  arXiv  Detail & Related papers  (2024-02-28T06:34:54Z)

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.