Minxian Xu

Jianmin Hu, Minxian Xu, Sa Wang et al.

Multi-turn conversation is a fundamental scenario in LLM applications, widely used in chatbots and AI agents. As the conversation evolves, historical tokens accumulate continuously. Existing systems cache their key-value (KV) pairs to avoid redundant computation. However, limited GPU memory (HBM) capacity often forces these KV caches to be offloaded to CPU memory or SSD, making KV cache reloads increasingly costly in terms of latency as the context grows. Meanwhile, the constrained HBM capacity also limits the maximum inference length, thereby restricting the number of turns that can be supported in a conversation. To address these two challenges, we propose SwiftCache, a collaborative inference system that enables heterogeneous models to share underutilized GPU memory and NVLink bandwidth within a server. Specifically, models with low KV cache demand donate idle GPU memory to store the prefix cache of high-demand models, allowing cross-model KV cache sharing over NVLink and avoiding slow PCIe transfers. SwiftCache further reduces memory pressure by keeping only the KV cache of the currently active layer in local GPU memory, thereby enabling longer-context inference. Our experiments on real-world workloads show that SwiftCache reduces P99 time-to-first-token (TTFT) by up to 69% and extends maximum context length by up to 3.98x compared to vLLM and SGLang, with minimal interference to co-located models.

Yifan Sun, Zhexiang Zhang, Jiantong Jiang et al.

Serving Mixture-of-Experts (MoE) large language models (LLMs) is challenging because dynamic request workloads interact with sparse expert routing, creating both data-parallel (DP) engine imbalance and expert-level hotspots. Existing LLM serving systems typically make these decisions in isolation: frontend schedulers route requests using coarse request counters, while backend expert balancers rely mainly on aggregate expert activation counts. This separation prevents the serving system from reacting to fine-grained engine pressure, backend MoE pressure, and source-dependent expert traffic. To address this gap, we propose Gimbal, a coordinated cross-level scheduling system for efficient MoE-based LLM serving. First, Gimbal presents a fine-grained DP-engine scheduler that uses online backend pressure signals, including key-value (KV) cache usage, remaining prefill work, queue pressure, and MoE expert pressure, to dispatch requests away from overloaded engines. Inside each engine, Gimbal further applies a lightweight prefill-aware queue ordering policy with aging to reduce head-of-line blocking without output-length prediction. Second, Gimbal extends expert load balancing with online source-DP-to-expert routing statistics and uses a heuristic guided by a mixed-integer nonlinear program (MINLP) to place experts while jointly considering expert load, source-aware communication, and migration stability. Our evaluation shows that Gimbal reduces average Time To First Token (TTFT) by 42.9% and average Time Per Output Token (TPOT) by 33.3% compared with the state-of-the-art serving system vLLM, while improving high-load request throughput by 3.0%.