Roomie is presented, a model serving orchestration architecture that predicts and avoids kernel-level interference between colocated DNNs, and reduces SLO violations by up to 3x, while maintaining comparable, and in many cases superior, goodput relative to existing approaches.
Abstract
As demand for DNN inference grows, GPU capacity is increasingly oversubscribed, forcing operators to colocate multiple models on the same device in both cloud and edge deployments. Whether colocation succeeds or violates SLOs depends on the temporal overlap of kernels from concurrently executing models -- an effect that existing serving systems either ignore or approximate using aggregate resource profiles that fail to capture temporal dynamics. This paper presents Roomie, a model serving orchestration architecture that predicts and avoids kernel-level interference between colocated DNNs. Roomie decouples offline kernel profiling from online interference prediction. It uses profiling only to extract per-kernel resource configurations, and predicts interference with an occupancy-based analytical model immune to profiler-induced timing distortion. A pairwise greedy heuristic then approximates multi-model interference in polynomial rather than exponential time, and an online placement algorithm then uses these estimates to assign each incoming model to the GPU that minimizes predicted slowdown. Our experimental evaluation compares Roomie against state-of-the-art solutions across both cloud-grade server clusters and embedded edge devices, demonstrating that Roomie reduces SLO violations (i.e., inference latency) by up to 3x, while maintaining comparable, and in many cases superior, goodput relative to existing approaches.
CELLServe formalizes SLO-constrained joint resource provisioning as an optimization problem with a dedicated algorithm, and introduces an opportunistic instance merging strategy for decode phase functions to reclaim fragmented resources.
Zejian Wang, Nan Lin, Zinuo Cai et al.· ACM Transactions on Architec...· 0 citations
TAILOR is presented, a token-aware inference framework that jointly optimizes offline partitioning and online routing for autoregressive transformer serving that reduces end-to-end latency and lowers OOM-induced fallback compared with static partitioning baselines, demonstrating robust inference under long-tailed token workloads.
Xiaoyao Huang, Remington R. Liu, Jie Wu· International Workshop on Qu...· 0 citations
LLMs scale Mixture-of-Experts (MoE) parameters for superior intelligence, but massive weights and dynamic computation impede efficient serving. Existing instance-level prefill-decode disaggregation isolates the phases on separate full-model replicas. As MoE weights grow, each instance may span tens to hundreds of GPUs, making resource allocation increasingly coarse. Configured prefill-to-decode ratios thus often mismatch demand, overprovisioning one phase while overloading the other. Prefill-decode colocation avoids this duplication, but existing Green Context solutions partition each GPU by phase and fix phase resources during a kernel. They cannot track resource changes across operations or layerwise variation in routed expert load, causing head-of-line blocking or idle reserved resources. Partitioning every GPU also leaves each phase with fewer local resources, forces wider parallelism and more communication, and lets prefill and decode traffic interfere on the shared network. We present ExpertPlex, which shares massive MoE experts across phases while disaggregating lightweight attention modules. Expert sharing eliminates over 95% of duplicate model weights and multiplexes dynamically sparse computation, while attention disaggregation reduces attention communication cost. ExpertPlex further uses (1) adaptive persistent kernels to schedule dynamic expert computation at tile granularity for efficient, isolated execution; (2) attention-initiated MoE communication to avoid network interference and enable cross-phase communication-computation overlap; and (3) a tile-to-cluster model to optimize these mechanisms for maximum goodput. Experiments serving MiniMax-M2.7 and GLM-5.1-FP8 show that ExpertPlex improves goodput by up to 2.01$\times$ over instance-level prefill-decode disaggregation and 1.66$\times$ over prefill-decode colocation.
Bingya Wu, Chao Jin, Zili Zhang et al.· 0 citations
Serverless multi-model LLM systems multiplex popularity-skewed model catalogs over shared GPU pools, yet typically schedule each request independently. Tool-using agents break this abstraction: a session repeatedly calls an LLM across short tool gaps, carries a long reusable KV prefix, and is judged by session completion time (SCT). Load-only routing can separate a continuation from both its model and KV state, while round-based model multiplexing can delay even a correctly placed continuation until the target model's next slot. Both failures are especially costly for hundred-billion-parameter models: their weights constrain residency, while long-context KV is expensive to reconstruct or move. We present Talaria, a session-aware serverless multi-model serving system that makes session continuity a joint placement-and-admission decision. Its router ranks placements by model residency, KV locality, and instance pressure, while soft reservations account for likely returns in the last serving instance's admission budget. Session-prefill (SP) admits budget-eligible continuations before the active model slot closes. An instance-local substrate keeps HBM addresses stable, preserves host-restorable KV, and stages weights across model switches. On a single TP=8 server, we replay 30 SWE-Bench model-sessions (960 calls) over three models, each with more than 100B total parameters. Against an otherwise identical round scheduler with SP, host-KV restoration, and D2D staging disabled, Talaria cuts p50 SCT from 1000 s to 189 s and p95 from 2296 s to 867 s, speedups of 5.3x and 2.6x.
Utopia Meng, Unicornt Zhao, Derek Li et al.· 0 citations
LLM serving is increasingly dominated by long and dynamic decode workloads from agents, reasoning models, and extended conversations. When bursty long-context demand exceeds deployed capacity, existing serving systems typically scale out by launching additional serving instances with model replicas. This instance-level elasticity increases KV capacity only by provisioning another full copy of the model, inheriting startup latency, memory overhead, and batch fragmentation. We present KernelFlume, a decode-centric architecture that disaggregates the stable projection/FFN path from core-attention computation: weight nodes execute dense projection/FFN kernels, while weightless attention nodes store token-range KV partitions and scale with request-state demand. To make this separation elastic, KernelFlume maintains a routing table that maps token ranges to attention-node endpoints. It updates routes at token boundaries and uses host-visible graph signals to drive pre-registered UCX endpoint communication outside the captured CUDA Graph. To preserve low per-token latency after disaggregation, KernelFlume combines query-first core-attention dispatch with inter-layer kernel pipelining, overlapping remote attention and communication with local projection/FFN work. On real GPU testbeds (intra-node A6000 and cross-node H100), under a dynamic long-context agentic workload serving Llama-3.1-8B, KernelFlume sustains flat p99 TPOTs of ~74 ms on A6000 and ~34 ms on H100, while lowering cost per million output tokens by up to 32% and 61%, respectively, relative to full-instance elastic scaling with ServerlessLLM, a state-of-the-art instance-startup method. Replaying the same trace at larger model scale in simulation projects a 56--66% cost reduction over ServerlessLLM, widening to 80--85% with cheaper heterogeneous attention-node hardware and persisting into the million-token context range.
Guangyu Xiang, Xueze Kang, Lin Zhang et al.· arXiv.org· 1 citation