Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference

• URL: http://arxiv.org/abs/2512.16134v1
• Date: Thu, 18 Dec 2025 03:45:05 GMT
• Title: Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference
• Authors: Jian Tian, Shuailong Li, Yang Cao, Wenbo Cui, Minghan Zhu, Wenkang Wu, Jianming Zhang, Yanpeng Wang, Zhiwen Xiao, Zhenyu Hou, Dou Shen,
• Abstract summary: Staggered Batch Scheduling (SBS) buffers requests to form optimal execution batches.<n> Load-Aware Global Allocation strategy balances computational load across DP units for both Prefill and Decode phases.<n>Our system reduces TTFT by 30%-40% and improves throughput by 15%-20% compared to state-of-the-art immediate scheduling baselines.
• Score: 17.27010833526918
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where schedulers can treat instances as black boxes, DP+EP architectures exhibit high internal synchronization costs. We identify that immediate request dispatching in such systems leads to severe in-engine queuing and parallelization bubbles, degrading Time-to-First-Token (TTFT). To address this, we propose Staggered Batch Scheduling (SBS), a mechanism that deliberately buffers requests to form optimal execution batches. This temporal decoupling eliminates internal queuing bubbles without compromising throughput. Furthermore, leveraging the scheduling window created by buffering, we introduce a Load-Aware Global Allocation strategy that balances computational load across DP units for both Prefill and Decode phases. Deployed on a production H800 cluster serving Deepseek-V3, our system reduces TTFT by 30%-40% and improves throughput by 15%-20% compared to state-of-the-art immediate scheduling baselines.

Related papers

• PLA-Serve: A Prefill-Length-Aware LLM Serving System [33.313531352453346]
  PLA-Serve identifies and disaggregates requests with different prompt lengths to reduce TTFT latency.<n>We observe that prompt-length variations lead to distinct bottlenecks, motivating an adaptive scheduling strategy.<n> PLA-Serve reduces prefill latency by over 30% compared to vanilla SG under prefill**-Lang**decode disaggregation.
  arXiv  Detail & Related papers  (2026-01-04T18:14:24Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• HyperFlexis: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling [19.154782641360253]
  Modern large language model (LLM) serving systems face challenges from highly variable requests with diverse lengths, priorities, and stage-specific service-level objectives (SLOs)<n>We present HyperFlexis, a unified LLM serving system that integrates algorithmic and system-level innovations to jointly optimize scheduling and scaling under multiple SLOs.
  arXiv  Detail & Related papers  (2025-08-21T18:40:20Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• Optimal Scheduling Algorithms for LLM Inference: Theory and Practice [6.043830060363904]
  This paper develops a theoretical framework that models routing and scheduling in Large Language Model inference systems.<n>We identify two key design principles-optimal tiling and dynamic resource allocation-that are essential for achieving high throughput.<n>We show that the Resource-Aware Dynamic (RAD) scheduler achieves throughput optimality under mild conditions.
  arXiv  Detail & Related papers  (2025-08-01T18:12:21Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage [6.805644270436825]
  We propose a novel large language model (LLM) serving system, semi-PD, characterized by disaggregated computation and unified storage.<n>Compared to state-of-the-art systems, semi-PD maintains lower latency at higher request rates, reducing the average end-to-end latency per request by 1.27-2.58x.
  arXiv  Detail & Related papers  (2025-04-28T15:00:03Z)
• Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving [22.66354939370058]
  Apt-Serve is a framework designed to enhance effective throughput in large language model (LLM) inference serving systems.<n>A new hybrid cache scheme combines KV cache with a memory-efficient hidden cache for reusable input hidden state vectors, allowing large batch sizes and improving request.<n>We show that Apt-Serve achieves up to 8.8x improvement in effective throughput compared to the state-of-the-art inference serving systems.
  arXiv  Detail & Related papers  (2025-04-10T06:51:23Z)
• APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs [81.5049387116454]
  We introduce APB, an efficient long-context inference framework.<n>APB uses multi-host approximate attention to enhance prefill speed.<n>APB achieves speeds of up to 9.2x, 4.2x, and 1.6x compared with FlashAttn, RingAttn, and StarAttn, respectively.
  arXiv  Detail & Related papers  (2025-02-17T17:59:56Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• GPU Cluster Scheduling for Network-Sensitive Deep Learning [15.926240223625165]
  We propose a novel GPU-cluster scheduler for distributed DL (DDL) workloads.<n>Our scheduler consists of three major components: (i) a classical delay scheduling algorithm to facilitate job placement and consolidation; (ii) a network-sensitive job preemption strategy; and (iii) an "auto-tuner" mechanism to optimize delay timers for effective delay scheduling.
  arXiv  Detail & Related papers  (2024-01-29T19:06:08Z)
• Tailored Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud System [54.588242387136376]
  We introduce KaiS, a learning-based scheduling framework for edge-cloud systems. First, we design a coordinated multi-agent actor-critic algorithm to cater to decentralized request dispatch. Second, for diverse system scales and structures, we use graph neural networks to embed system state information. Third, we adopt a two-time-scale scheduling mechanism to harmonize request dispatch and service orchestration.
  arXiv  Detail & Related papers  (2021-01-17T03:45:25Z)

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.