EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language Models

arXiv:2609.31551 · cs.DC, cs.LG, cs.PF · Submitted 2026-09-25 · Read on arXiv

cs.DC, cs.LG, cs.PF

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/fixie-ai/ultravox

Terminology

• Decode — 39× in this paper · explained in 2 episodes
• Embeddings — 8× in this paper · explained in 2 episodes
• Hybrid Auto Selection — 7× in this paper
• Pruning — 6× in this paper · explained in 4 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• KV cache — 4× in this paper · explained in 3 episodes
• International Conference on Machine Learning — 3× in this paper
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Bayesian Optimization — 2× in this paper · explained in 3 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Multi-Process Service — 2× in this paper
• Symposium on Operating Systems Design and Implementation — 2× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• NVIDIA Inference Xfer Library — 1× in this paper
• Streaming Multiprocessor — 1× in this paper
• Texture Processing Cluster — 1× in this paper
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Yi: Open Foundation Models by 01.AI
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen2.5-VL Technical Report
• HydraInfer: Hybrid Disaggregated Scheduling for Multimodal Large Language Model Serving
• Gemma 2: Improving Open Language Models at a Practical Size
• Niyama : Breaking the Silos of LLM Inference Serving
• semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage
• LLaVA-OneVision: Easy Visual Task Transfer
• Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving
• Fast Distributed Inference Serving for Large Language Models

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing