LAPS: A Length-Aware-Prefill LLM Serving System
LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling policies that fail to adapt to heterogeneous workload characteristics. We observe that prompt-length variations lead to distinct performance bottlenecks, motivating an adaptive scheduling strategy. LAPS disaggregates multi-turn long-prefill requests from short-prefill ones and introduces a length-aware smart batching mechanism for short-prefill workloads. It adopts a dual-queue design that supports temporal disaggregation on a single prefill instance or spatial disaggregation across multiple instances. For short-prefill batches, a batch waiting window and CUDA Graph-based clustering mitigate interference from heterogeneous computation, reducing batching delay and lowering average latency. In real multi-turn workloads, LAPS reduces prefill latency by over 30\% compared to vanilla SGLang under prefill-decode disaggregation, and further decreases SLO violations by 28\% in multi-instance deployments with vanilla data-parallel configuration. Compared to the SGLang router with load balancing, it further lowers SLO violations by 12\% in multi-GPU settings. Under high concurrency and mixed-request scenarios, LAPS improves request throughput by 35\% serving Qwen2.5-32B model for prefill instance, demonstrating its effectiveness in optimizing heterogeneous LLM serving workloads.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction
Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Predicting output lengths in advance makes it possible to adopt length-…
Reinforcement LearningMedha: Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations
As large language models (LLMs) handle increasingly longer contexts, serving long inference requests of millions of tokens presents unique challenges. We show that existing work for long context inference is largely base…
BlockingChunkingSchedulingCompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily…
Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models
During inference for transformer-based large language models (LLM), prefilling is the computation of the key-value (KV) cache for input tokens in the prompt prior to autoregressive generation. For longer input prompt len…
An Interpretable Latency Model for Speculative Decoding in LLM Serving
Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified by a larger target model in parallel. While prior work demonstrates s…