LLM Inference in a Flash!

• URL: http://arxiv.org/abs/2609.16161v1
• Date: Mon, 14 Sep 2026 18:04:30 GMT
• Title: LLM Inference in a Flash!
• Abstract summary: Large Language Models (LLMs) have shown impressive capabilities across a range of natural language processing tasks.<n>We present an end-to-end integer-only quantization approach to eliminate expensive floating-point computations.
• Score: 66.43896490006965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have shown impressive capabilities across a range of natural language processing tasks, and LLM inference has emerged as a critical workload for enabling downstream applications. The demands of serving LLM inference are becoming increasingly challenging as requests shift toward longer sequences and heavier inference, driven by retrieval-augmented generation, inference-time compute scaling, and long-context applications. Additionally, these challenges are compounded by hardware trends, as memory capacity and communication bandwidth are not scaling as fast as increases in workload complexity. Compute-in-Flash is a promising solution to address memory bandwidth limitations by moving computation close to memory, and to exploit the large capacity of SSD technologies. However, it is challenging to deploy LLMs on these systems as they lack support for high-precision floating point operations and have limited write endurance. In our work, we aim to address these challenges by designing inference algorithms to enable LLM inference on Flash compute-in-memory devices. We present an end-to-end integer-only quantization approach to eliminate expensive floating-point computations. To address the limited write endurance, we design a dictionary-based KV cache compression strategy based on sparse dictionary coding that represents each KV vector as a linear combination of static dictionary vectors. These algorithmic improvements enable us to exploit the benefits of Compute-in-Flash for both model weights and KV cache, and to minimize expensive data transfer operations. Across Llama-3.1-8B and Qwen-2.5-7B, our combined method exhibits limited accuracy degradation while reducing dynamic KV cache traffic by 15$\times$.

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)
• FLARE: Diffusion for Hybrid Language Model [72.60770374799634]
  FLARE is a systematic conversion framework for hybrid-attention large language models.<n>It combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising.<n>Our results suggest practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives.
  arXiv  Detail & Related papers  (2026-06-01T06:58:15Z)
• A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints [4.636275494777427]
  We introduce the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints.<n>We derive rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth.<n>Our results show that the predicted stability conditions are highly accurate, with deviations typically within 10%.
  arXiv  Detail & Related papers  (2026-05-06T07:42:26Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [72.27673320976933]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding.<n>Current caching techniques accelerate decoding by storing full-layer states, yet impose substantial memory usage.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints [14.341123057506827]
  Large Language Models (LLMs) are indispensable in today's applications, but their inference procedure demands significant computational resources.<n>This paper formulates LLM inference optimization as a multi-stage online scheduling problem.<n>We develop a fluid dynamics approximation to provide a tractable benchmark that guides algorithm design.
  arXiv  Detail & Related papers  (2025-04-15T16:00:21Z)
• FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving [9.386969461835433]
  FlashInfer is a customizable and efficient attention engine for large language models (LLMs)<n>It tackles KV-cache storage heterogeneity using block-sparse format and composable formats to optimize memory access and reduce redundancy.<n>It also offers a customizable attention template, enabling adaptation to various settings through Just-In-TimeJIT compilation.
  arXiv  Detail & Related papers  (2025-01-02T02:02:20Z)
• Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference [2.9302211589186244]
  Large language models (LLMs) have transformed natural language processing, enabling machines to generate human-like text and engage in meaningful conversations. Developments in computing and memory capabilities are lagging behind, exacerbated by the discontinuation of Moore's law. compute-in-memory (CIM) technologies offer a promising solution for accelerating AI inference by directly performing analog computations in memory.
  arXiv  Detail & Related papers  (2024-06-12T16:57:58Z)

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.