CORTEXA
← Browse
arxivcs.LG2026-07-09

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving

Yuanjie Zhu, Liangwei Yang, Ke Xu, Weizhi Zhang, Shanghao Li, Zihe Song, Philip S. Yu

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.

View free PDFSource page

Related papers

arxivcs.LG2026-06-27

DiLaServe: High SLO Attainment Serving for Diffusion Language Models

Tzu-Tao Chang, Benjamin Yuanyang Hong, Kiet Pham, Shivaram Venkataraman

Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple tokens in parallel during each denoising step, they offer higher inference throughput while maintaining competitive quality. Ho…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-02

Training Hybrid Block Diffusion Language Models with Partial Bidirectionality

Pranshu Chaturvedi, Parth Shroff, Tarun Suresh, Hangoo Kang, Kaiyue Wen

High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rather than compute-bound: each decoding step must stream the accumulated key/value (KV) cache from memory, so bandwidth demand grows…

View free PDFSource page
arxivcs.DCcs.LG2026-07-13

FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving

Yaqi Qiao, Ping He, Songrun Xie, Ayush Barik, Chensong Zhang, Zhengzhong Tu, et al.

Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge. Unlike autoregressive decoding, diffusion inference repeatedly updates high-dimensional spatial or temporal latents over many denoisin…

View free PDFSource page
arxivcs.ARcs.AIcs.ETcs.LG2026-07-29

LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM Serving

Ming-Yen Lee, Hanchen Yang, Faaiq Waqar, Harsono Simka, Tushar Krishna, Muhammed Ahosan Ul Karim, et al.

The energy consumption of Large Language Model (LLM) serving is becoming a major system challenge as deployment scales, driven by hardware power and thermal constraints and rising electricity costs. A key contributor to chip energy dissipation is data movement between limited on-…

View free PDFSource page