DualPace: Decoupled Scheduling and Cooperative GPU--CPU Decoding for LLM Serving

Overview & Synopsis

Large language model (LLM) serving relies on batching to improve inference throughput, but the key-value (KV) cache grows with sequence length and limits GPU-resident concurrency. CPU offloading can expand KV capacity using host memory, yet existing systems remain largely GPU-gated: CPU-resident requests make progress only when the GPU scheduler exposes suitable overlap opportunities. As a result, host memory and CPU compute cannot act as an independent serving resource, leading to bursty CPU-side progress and inflated tail inter-token latency (ITL) under load. We present DualPace, an LLM serving runtime that turns the host into an independently scheduled decode engine. DualPace separates scheduling authority across two engines: the GPU engine executes prefills and GPU-resident decodes, while an AMX-enabled CPU engine independently batches and advances CPU-resident decodes. The engines are decoupled in scheduling but cooperative in execution: the CPU can execute a complete decode iteration locally or selectively invoke GPU Dense Assist for dense stages, while offline profiles guide hardware-specific batching and routing. Our evaluations show that, in decode-oriented scenarios, DualPace improves serving throughput by 6.9--43.2\% over NEO, a state-of-the-art open-source CPU-offloading system, and by 11.5--90.6\% over vLLM, a widely used GPU serving system, while maintaining the same level of latency. DualPace also preserves NEO's P99 time-to-first-token (TTFT) advantage over vLLM while sustaining 7.3--50.5\% higher request rates than NEO at the same level of P99 ITL.