Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling
원문 초록
Having large batch sizes is one of the most critical aspects of increasing the accelerator efficiency and the performance of DNN model inference. However, existing model serving systems cannot achieve adequate batch sizes while meeting latency objectives as these systems eagerly dispatch requests to accelerators to minimize the accelerator idle time. We propose Symphony, a DNN serving system that explores deferred batch scheduling to optimize system efficiency and throughput. Further, unlike other prior systems, Symphony's GPU usage is load-proportional: it consolidates workloads on the appropriate number of GPUs and works smoothly with cluster auto-scaling tools. Symphony consists of two core design points. First, Symphony defines a schedulable window in which a batch of inference requests can be dispatched. This window is computed in order to improve accelerator efficiency while meeting the request's SLO. Second, Symphony implements a scalable, low-latency, fine-grained coordination scheme across accelerators to dispatch and execute requests in the schedulable window. Through extensive scheduler-only benchmarks, we demonstrate that Symphony can schedule millions of requests per second and coordinate thousands of GPUs while also enabling robust autoscaling that adapts to workload changes. Symphony outperforms prior systems by achieving 5x higher goodput when given the same number of GPUs and 60% reduction in GPUs when given the same workload.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning
ConsumerBench: Benchmarking Generative AI Applications on End-User Devices
Vine Copulas as Differentiable Computational Graphs
FlashDMoE: Fast Distributed MoE in a Single Kernel
Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts
CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.