FOCUS: DLLMs Know How to Tame Their Compute Bound

• URL: http://arxiv.org/abs/2601.23278v1
• Date: Fri, 30 Jan 2026 18:52:06 GMT
• Title: FOCUS: DLLMs Know How to Tame Their Compute Bound
• Authors: Kaihua Liang, Xin Tan, An Zhong, Hong Xu, Marco Canini,
• Abstract summary: FOCUS is an inference system designed for Diffusion Large Language Models (DLLMs)<n>It focuses computation on decodable tokens and evicting non-decodable ones on-the-fly.<n>It achieves up to 3.52$times$ throughput improvement over the production-grade engine LMM.
• Score: 10.298643186738799
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is parallelized over token blocks, only a small subset of tokens is decodable at each diffusion step, causing most compute to be wasted on non-decodable tokens. We further observe a strong correlation between attention-derived token importance and token-wise decoding probability. Based on this insight, we propose FOCUS -- an inference system designed for DLLMs. By dynamically focusing computation on decodable tokens and evicting non-decodable ones on-the-fly, FOCUS increases the effective batch size, alleviating compute limitations and enabling scalable throughput. Empirical evaluations demonstrate that FOCUS achieves up to 3.52$\times$ throughput improvement over the production-grade engine LMDeploy, while preserving or improving generation quality across multiple benchmarks. The FOCUS system is publicly available on GitHub: https://github.com/sands-lab/FOCUS.

Related papers

• ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models [4.273730624882391]
  Vision-Language Models (VLMs) are expensive because the LLM processes hundreds of largely redundant visual tokens.<n>We show that neither signal alone is sufficient: fusing them consistently improves performance compared to unimodal visual token selection (ranking)<n>We propose textbfConsensusDrop, a training-free framework that derives a emphconsensus ranking by reconciling vision encoder saliency with query-aware cross-attention.
  arXiv  Detail & Related papers  (2026-02-01T00:28:55Z)
• CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models [27.070045950001532]
  CD4LM is a framework that decouples training from inference.<n>On GSM8K, CD4LM matches the LLaDA baseline with a 5.18x wall-clock speedup.
  arXiv  Detail & Related papers  (2026-01-05T16:09:22Z)
• Continuous Autoregressive Language Models [56.49239051750678]
  We introduce Continuous Autoregressive Language Models (CALM)<n>CALM uses a high-fidelity autoencoder to compress a chunk of K tokens into a single continuous vector.<n>We develop a comprehensive likelihood-free framework that enables robust training, evaluation, and controllable sampling.
  arXiv  Detail & Related papers  (2025-10-31T17:58:11Z)
• Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models [82.87985794856803]
  Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks.<n>Recently, Diffusion Language Models (DLMs) have emerged as a promising alternative architecture.
  arXiv  Detail & Related papers  (2025-10-05T10:50:52Z)
• Sequential Diffusion Language Models [110.06562906987052]
  Diffusion language models (DLMs) have strong theoretical efficiency but are limited by fixed-length decoding and incompatibility with key-value caches.<n>We introduce Next Sequence Prediction (NSP), which unifies next-token and next-block prediction.<n>We propose Sequential Diffusion Language Model (SDLM), which can retrofit pre-trained autoregressive language models (ALMs) at minimal cost.
  arXiv  Detail & Related papers  (2025-09-28T17:59:15Z)
• 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)
• Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection [49.15148871877941]
  Next-token distribution outputs offer a theoretically appealing approach for detection of large language models (LLMs)<n>We propose the Perplexity Attention Weighted Network (PAWN), which uses the last hidden states of the LLM and positions to weight the sum of a series of features based on metrics from the next-token distribution across the sequence length.<n>PAWN shows competitive and even better performance in-distribution than the strongest baselines with a fraction of their trainable parameters.
  arXiv  Detail & Related papers  (2025-01-07T17:00:49Z)
• Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles [23.134664392314264]
  Tokenization is associated with many poorly understood shortcomings in language models (LMs)<n>This work studies how tokenization impacts model performance by analyzing and comparing models with their byte-level counterparts.<n>We introduce the Byte-Token Representation Lemma, a framework that establishes a mapping between the learned token distribution and its equivalent byte-level distribution.
  arXiv  Detail & Related papers  (2024-10-11T23:30:42Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)

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.