Speculative reduction is proposed, which initiates data transfer before the top barrier and ensures correctness via lightweight validation during low-latency inference, which reduces synchronization overhead during low-latency inference.
Abstract
The rise of reasoning models and agentic systems has made LLM token-generation latency a key bottleneck. Unlike chatbots, whose latency gains saturate at human reading speed, these systems generate intermediate reasoning tokens not consumed by humans. Thus, per-token latency directly determines end-to-end response time. Low-latency inference uses minimal batching, making token generation bandwidth-bound. Tensor Parallelism addresses this by sharding model weights across GPUs and loading them in parallel. However, scaling to more GPUs introduces All-Reduce overheads that grow with GPU count. Removing All-Reduce improves token throughput by 43% for Llama-3.1-8B on 8 H200 GPUs. We propose Synchronization-Free All-Reduce (SiFAR), which reduces synchronization overhead during low-latency inference. Existing oneshot and twoshot algorithms incur overheads from barriers before and after communication. First, we find that the bottom barrier in oneshot enforces a WAW dependency and eliminate it by co-designing communication and model execution to enable dual buffering. However, oneshot scales poorly with GPU count. Twoshot performs better at higher TP degrees but incurs an unavoidable bottom barrier. To overcome this, we leverage in-switch reduction in modern switches. We propose redundant pull, where each GPU reduces the full All-Reduce payload at the switch. This improves oneshot scalability while retaining its no-bottom-barrier advantage. Finally, to reduce top-barrier overhead, we observe that each decode step issues multiple All-Reduce operations, keeping GPUs tightly synchronized after the first. We therefore propose speculative reduction, which initiates data transfer before the top barrier and ensures correctness via lightweight validation. SiFAR reduces All-Reduce latency by up to 52% and improves end-to-end throughput by 18.6% for Llama-3.1-8B and 13.1% for Qwen3.5-397B-17B at TP=8.
LLMVisor is presented, a roofline-guided latency attribution model that captures the memory-bound and compute-bound phases via a concise piecewise-linear form over features proportional to FLOPs and memory I/O traffic and runs efficiently at microsecond scale.
Shuowei Jin, Xueshen Liu, Jiaxin Shan et al.· 2 citations
CoRun is presented, a scheduling-based system that achieves deterministic inference without requiring batch invariance, and employs isolated prefill and fixed-shape batched decode to handle the two stages of LLM inference, respectively, leveraging CUDA graphs for efficient execution and simplified implementation.
Shiju Zhao, Jiacheng Yang, Qihang Chen et al.· 0 citations
Results show that energy-aware serving should jointly optimize both request energy and token energy, rather than only reducing per-token energy cost, and substantially narrows the dense-vs-MoE token-energy gap.
P. Vellaisamy, Vanessa Lam, Shawn Blanton et al.· 0 citations
Existing Large Language Model (LLM) inference systems often rely on static model placement and scheduling policies, which struggle to handle heterogeneous and dynamic real-world workloads. The key challenge is to adapt serving strategies to workload fluctuations while keeping reconfiguration overhead minimal. In this paper, we present OrionInfer, an adaptive LLM serving system that aligns inference strategies with real-time demand. OrionInfer introduces three key techniques: (1) runtime switching between data parallelism and tensor parallelism with negligible overhead; (2) an efficient inference pipeline that preserves batching efficiency during parallelism transitions; and (3) live-migration-based load balancing to alleviate memory pressure and improve resource utilization. Evaluations across multiple model scales show that OrionInfer delivers robust performance under diverse serving scenarios. In end-to-end serving, it reduces average TTFT by up to 25% over DP-priority configurations under low loads and lowers P99 tail latency by 50%--90% over TP-priority configurations under most high-traffic settings. In disaggregated prefill serving, OrionInfer improves prefill completion time (PCT) SLO attainment by up to 16.5 percentage points over DP-priority static baselines and reduces P99 PCT by up to 74.7% over TP-priority static baselines. Compared with dynamic baseline, OrionInfer provides better tail-latency stability, reducing P99 PCT by 38.6%--40.8% while avoiding the extra memory footprint.
Jingqi Feng, Guang Yang, Yukai Huang et al.· Proceedings of the 32nd ACM...· 0 citations
Long-context reasoning for large language models (LLMs) is becoming increasingly important, but training over long sequences remains challenging due to massive memory and communication requirements. Sequence parallelism has emerged as an essential technique for addressing bottlenecks in long sequence LLM training. However, we observe that existing sequence parallelism methods are batch-agnostic and apply uniform sequence partitioning across all batch sizes, resulting in inefficient communication. In this paper, we introduce Batch- Aware Sequence Parallelism (BASP), a sequence parallelism approach that leverages batch structure to reduce communication overhead. BASP exploits batch structure by partitioning GPUs into disjoint sequence-parallel groups according to the micro- batch size. This design reduces the all-to-all communication group size, thereby localizing communication and improving training efficiency. Experimental results on an NVIDIA A100 cluster show that BASP improves end-to-end training time by up to 1.17 - 1.31x in Llama and Qwen models compared to standard sequence parallel baselines, while preserving identical model accuracy and memory usage.
This work presents a distributed inference framework that integrates speculative decoding across edge and cloud, and shifts the bulk of computation to the edge, significantly lowers inference time and cloud cost, and preserves the accuracy of the big model without any retraining requirement.
D. J. Bajpai, K. Upadhyay, M. Hanawal· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
