Papers for
gpu infrastructure teams
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Jointserve reduces multi-model agent delays on limited gpu memory
JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs
Abstract: LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weights. This shift breaks a hidden assumption of today's serving systems: that the working set of models fits in GPU memory. On the memory-constrained GPUs typical of private and edge deployments, naive whole-model swapping serializes weight transfer with computation and, without host-backed KV restoration, discards session state at a switch. We present JointServe, a serving system that treats weight shards and KV blocks as residency objects competing for one unified memory budget. JointServe exploits three structural properties of agent workloads (directed calls, gapped execution, and dual-state residency) to prepare models before they are called: an intent signal parsed from the caller's own output stream triggers prefetch during generation, partial k* residency reduces switching to incremental layers, and a preemptive transfer scheduler protects live-session KV with a guaranteed bandwidth share. A carve-out control step adjusts the weight/KV allocation as workload demands change. Evaluations show that JointServe reduces session completion time by 21.7% over the strongest whole-model swap baseline and stays usable in a crash regime where every whole-model swap baseline fails to finish (a 46-fold gap). On replayed SWE-bench, tau-bench, and OSWorld traces, it cuts session completion time by up to 49% and lifts SLO attainment from 2.8-24.5% to 76.8-100%.
Video diffusion transformers prune experts to save memory and improve use
DIET: Deletion-response Expert Trimming for Video Diffusion Transformers
Abstract: Video diffusion transformers (DiTs) increasingly adopt mixture-of-experts (MoE) architectures to reduce active computation, but their full expert storage remains costly. Existing one-shot pruning criteria mainly rely on static activation or routing statistics and cannot capture layer-level re-routing after expert deletion. We introduce DIET, a training-free expert pruning framework based on deletion responses. A single all-expert calibration pass records expert outputs and router states for matched conditional and unconditional tokens. Candidate deletions are then replayed from cached tensors, requiring no additional model forward passes. The resulting deletion-response signatures characterize each expert by the changes induced when it is removed. DIET selects retained experts by minimizing Overall Diversity Loss (ODL), which preserves directional coverage in signature space, and combines intra-layer local search with an inter-layer regression-guided budget search to allocate experts across layers. On LingBot-Video 30B-A3B, pruning 50% of experts (6,144 to 3,072) reduces the checkpoint from 57 GB to 30 GB and enables single-card deployment on a 48 GB GPU without fine-tuning. Under a fixed 284-case VBench protocol, the VBench Total increases from 0.7941 to 0.8115. Across tested retention budgets, DIET consistently outperforms competitive pruning baselines adapted from large language models.