English(EN) BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving

BlockServe框架将dLLM服务吞吐量提升高达10.6倍

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-09 20:48

研究人员开发了BlockServe，一个旨在提高扩散式大语言模型（dLLM）服务效率的新型框架。该系统通过实现块粒度调度来解决批处理中异构收敛速率的挑战，该调度允许在块边界立即驱逐已完成的请求。BlockServe还集成了混合状态执行和面向计算的准入控制器，以扩大批处理容量。在Dream和LLaDA基准测试上的实验表明，与Fast-dLLM++等现有方法相比，BlockServe在保持生成质量的同时可以实现更高的吞吐量。 AI

影响这项研究提供了一种优化dLLM推理的新方法，有望实现这些模型更高效、更具成本效益的部署。

排序理由该条目描述了一个新框架及其在研究论文中提出的性能评估。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一个新框架及其在研究论文中提出的性能评估。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: infra, paper; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 58 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-07-09 20:48

BlockServe：面向高吞吐量扩散式大模型服务的块级连续批处理

Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and t…

本文如何被排名

报道来源 [1]

BlockServe：面向高吞吐量扩散式大模型服务的块级连续批处理

相关实体

相关话题