{"slug": "blockserve-block-grained-continuous-batching-for-high-throughput-diffusion-llm", "title": "BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving", "summary": "Researchers propose BlockServe, a continuous batching framework for diffusion large language models that uses block-grained scheduling to eliminate compute bubbles and tail latency caused by convergence heterogeneity. The system achieves 1.9–10.6× throughput over Fast-dLLM on Dream and LLaDA benchmarks, establishing a foundation for high-throughput offline dLLM inference.", "body_md": "arXiv:2607.08930v1 Announce Type: new\nAbstract: 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 tail latency. We present BlockServe, a continuous batching framework that integrates block-grained scheduling -- immediately evicting completed requests at block boundaries -- with mixed-state execution that extends dual cache and parallel decoding to heterogeneous batches via gather-scatter indexing. Furthermore, a compute-aware admission controller expands effective batch capacity through token-budgeted refill. On Dream and LLaDA across five benchmarks, BlockServe achieves 1.9--10.6$\\times$ throughput over Fast-dLLM with comparable generation quality, establishing block-grained scheduling as a foundation for high-throughput offline dLLM inference.", "url": "https://wpnews.pro/news/blockserve-block-grained-continuous-batching-for-high-throughput-diffusion-llm", "canonical_source": "https://arxiv.org/abs/2607.08930", "published_at": "2026-07-13 04:00:00+00:00", "updated_at": "2026-07-13 04:27:11.895040+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-infrastructure"], "entities": ["BlockServe", "Fast-dLLM", "Dream", "LLaDA"], "alternates": {"html": "https://wpnews.pro/news/blockserve-block-grained-continuous-batching-for-high-throughput-diffusion-llm", "markdown": "https://wpnews.pro/news/blockserve-block-grained-continuous-batching-for-high-throughput-diffusion-llm.md", "text": "https://wpnews.pro/news/blockserve-block-grained-continuous-batching-for-high-throughput-diffusion-llm.txt", "jsonld": "https://wpnews.pro/news/blockserve-block-grained-continuous-batching-for-high-throughput-diffusion-llm.jsonld"}}