HydraInfer: Hybrid Disaggregated Scheduling for Multimodal Large Language Model Serving

Abstract: Multimodal LLMs (MLLMs) have been rapidly advancing, enabling cross-modal understanding and generation, and propelling artificial intelligence towards artificial general intelligence. However, existing MLLM inference systems are typically designed based on the architecture of LLMs, integrating image processing and language processing as a single scheduling unit. This design struggles to accommodate the heterogeneous demands of different stages in terms of computational resources, memory access patterns, and service-level objectives (SLOs), leading to low resource utilization and high request latency, ultimately failing to meet the service requirements of diverse inference scenarios. To address these challenges, we propose HydraInfer, an efficient MLLM inference system that adopts a Hybrid Encode-Prefill-Decode (EPD) Disaggregation architecture. By scheduling the three stages - encode, prefill, and decode - onto separate heterogeneous inference instances, the system flexibly reallocates resources across stages, significantly reducing idle computation, alleviating resource bottlenecks, and improving overall system throughput and scalability. In addition, HydraInfer supports a stage-level batching strategy that enhances load balancing, enables parallel execution of visual and LLMs, and further optimizes inference performance. Experiments under real multimodal inference workloads demonstrate that HydraInfer can achieve up to 4x higher inference throughput compared to state-of-the-art systems (e.g., vLLM) on a single-node 8xH800 GPU cluster, while meeting the 90th percentile request SLO.