QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization

• URL: http://arxiv.org/abs/2506.22396v1
• Date: Fri, 27 Jun 2025 17:10:32 GMT
• Title: QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization
• Abstract summary: Inference accounts for the majority of latency and energy consumption in large language models.<n>We introduce QuickSilver, a modular, token-level framework that enables semantic adaptivity at inference time without altering model weights or structure.
• Score: 7.188043811595143
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency has seen extensive progress, runtime optimization remains a key bottleneck, particularly under autoregressive decoding. Existing approaches -- such as pruning, quantization, early exits, and speculative decoding -- often require retraining, architectural changes, or disrupt decoding compatibility. We introduce QuickSilver, a modular, token-level framework that enables semantic adaptivity at inference time without altering model weights or structure. QuickSilver integrates four synergistic mechanisms: (i) Dynamic Token Halting, which halts computation for tokens with converged representations; (ii) KV Cache Skipping, which selectively suppresses memory writes to reduce attention overhead; and (iii) Contextual Token Fusion, which collapses redundant tokens into shared paths to shrink sequence length. Unlike speculative decoding or MoE routing, QuickSilver operates entirely on frozen, dense models and requires no auxiliary networks. Applied to GPT-2 and Llama-2 across WikiText-103 and C4, QuickSilver achieves up to 39.6% FLOP reduction with negligible perplexity degradation (<=0.2).

Related papers

• Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding [51.48425605758328]
  We present Faster Flash Decoding (FFD), a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding.<n>FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning.<n>It achieves up to 11.6x kernel-level speedup and scaling to 256K context length, with 2.37x end-to-end throughput improvement.
  arXiv  Detail & Related papers  (2026-08-31T15:13:20Z)
• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation [0.0]
  Large Language Models generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length.<n>Recent compression methods mitigate this cost via token merging.<n>We propose a training-free, dual-component framework for KV cache compression that addresses these limitations.
  arXiv  Detail & Related papers  (2026-05-19T17:44:56Z)
• Stateful Token Reduction for Long-Video Hybrid VLMs [69.6930118088911]
  We study query-conditioned token reduction for hybrid video vision-language models (VLMs)<n>We propose a low-to-high progressive reduction schedule and a unified language-aware scoring mechanism for both attention and Mamba blocks.<n>Under an aggressive compression setting, our approach delivers substantial prefilling speedups with near-baseline accuracy at test time.
  arXiv  Detail & Related papers  (2026-02-27T08:11:06Z)
• RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs [5.782015253162346]
  Residual binarization enables matmul-free inference by stacking binary layers.<n>We propose RaBiT, a novel quantization framework that resolves coadaptation by algorithmically enforcing a residual hierarchy.<n>RaBiT achieves state-of-the-art performance, rivals even hardware-intensive Vector Quantization (VQ) methods, and delivers a $4.49times$ inference speed-up over full-precision models.
  arXiv  Detail & Related papers  (2026-02-05T06:41:11Z)
• ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding [37.86179431483446]
  Autoregressive models (ARMs) are hindered by slow sequential inference.<n>We introduce ReFusion, a novel masked diffusion model that achieves superior performance and efficiency.<n>ReFusion bridges the performance gap to strong ARMs while maintaining a 2.33$times$ average speedup.
  arXiv  Detail & Related papers  (2025-12-15T17:41:19Z)
• InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation [56.694702609077495]
  Long-sequence processing is a critical capability for modern large language models.<n>InfLLM-V2 is a trainable sparse attention framework that seamlessly adapts models from short to long sequences.<n>In experiments, InfLLM-V2 is 4$times$ faster than dense attention while retaining 98.1% and 99.7% of the performance.
  arXiv  Detail & Related papers  (2025-09-29T12:08:33Z)
• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [58.044803442346115]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive computational complexity and memory overhead during inference.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention via delayed bidirectional sparse caching.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning [60.37610817226533]
  Chain-of-thought (CoT) reasoning encourages step-by-step intermediate reasoning during inference.<n>CoT introduces substantial computational overhead due to its reliance on autoregressive decoding over long token sequences.<n>We present R-Stitch, a token-level, confidence-based hybrid decoding framework that accelerates CoT inference.
  arXiv  Detail & Related papers  (2025-07-23T08:14:36Z)
• AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism [17.858104076062897]
  Large language models (LLMs) are increasingly used for long-content generation.<n>We propose AdaDecode, which accelerates decoding without requiring auxiliary models or changes to the original model parameters.<n>AdaDecode consistently achieves superior decoding throughput with up to 1.73x speedup.
  arXiv  Detail & Related papers  (2025-06-04T08:32:30Z)
• ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs [7.958429361868486]
  We propose ZSMerge, a dynamic KV cache compression framework for efficient cache management.<n>ZSMerge significantly enhances memory efficiency and inference speed with negligible performance degradation.
  arXiv  Detail & Related papers  (2025-03-13T03:36:03Z)
• LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification [42.54363549922909]
  LongSpec is a framework that addresses the challenges of efficient inference over long contexts.<n>LongSpec achieves up to a 3.26x speedup over strong Flash Attention baselines.<n>The code is available at https://github.com/sail-sg/LongSpec.
  arXiv  Detail & Related papers  (2025-02-24T18:53:31Z)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings.<n>In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency.<n>We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models [58.3342517278868]
  This paper describes the design of Mixed-precision AutoRegressive LINear kernels. It shows that batchsizes up to 16-32 can be supported with close to maximum ($4times$) quantization speedup. MarLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining.
  arXiv  Detail & Related papers  (2024-08-21T16:10:41Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens.<n>Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)
• LoCoCo: Dropping In Convolutions for Long Context Compression [77.26610232994508]
  This paper presents a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo) LoCoCo employs only a fixed-size Key-Value ( KV) cache, and can enhance efficiency in both inference and fine-tuning stages.
  arXiv  Detail & Related papers  (2024-06-08T01:35:11Z)

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.