Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2405.14636

PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services

Zheming Yang·Yuanhao Yang·Chang Zhao·Qi Guo·Wenkai He·Wen Ji
View original source ↗Read source document ↗Export metadata ↓

Abstract

With the rapid growth in the number of large language model (LLM) users, it is difficult for bandwidth-constrained cloud servers to simultaneously process massive LLM services in real-time. Recently, edge-cloud infrastructures have been used to improve the processing efficiency of large-scale LLM services. However, the diversity of task requirements and the dynamics of resources pose great challenges to inference scheduling, leading to the wastage of many resources. In this paper, we present PerLLM, a personalized inference scheduling framework with edge-cloud collaboration designed for diverse LLM services. For the complexity of multiple constraints and the decision-making process of edge-cloud collaboration, we integrate the upper confidence bound algorithm based on the constraint satisfaction mechanism in PerLLM. For diverse LLM services, PerLLM can optimize service scheduling and resource allocation solutions within the edge-cloud infrastructure to meet processing time requirements while minimizing energy costs. Experimental results from different model deployments show that PerLLM can effectively meet the processing time requirements of personalized services. Compared to other methods, PerLLM achieves 2.2x, 2.1x, and 1.6x throughput and reduces the energy cost by more than 50%.

Explore related subjects

cs.DCcs.NI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Zheming Yang, Yuanhao Yang, Chang Zhao, Qi Guo, Wenkai He, Wen Ji. 2024-05-23. PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services. https://arxiv.org/abs/2405.14636

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Co-Fabric: Breaking Host-Domain Boundaries for Unified xPU Interconnection

Large-model parameters have grown beyond the capacity of a single xPU, dispersing across multiple xPUs spanning distinct host domains, where xPU-to-xPU communication dominates overall system efficiency. Existing scale-up interconnect remains inadequate: network-based solutions built on Ethernet--such as RoCE (RDMA over Converged Ethernet)--introduce specific message-semantics and protocol-stack characteristics, and rely on fragmented per-host addressing, while conventional host-based fabrics are confined to a single host domain and lack cross-host unified addressing. This paper presents Co-Fabric, a bus-based interconnect that, unlike conventional bus designs, breaks host-domain boundaries to deliver unified xPU interconnection for scale-up superpods. Co-Fabric makes three contributions: a streamlined four-layer protocol stack achieving nanosecond-scale processing latency with native reliability; a cross-domain scaling and P2P mechanism that routes using port identifiers embedded in the packet header; and a unified address space built on shadow-device auto-enumeration. On a 64-xPU 3D-Mesh system, Co-Fabric cuts inter-node communication latency by over 50% and improves bandwidth by 2-5x over RoCE, accelerating DeepSeek R1 inference by 30%-80%. Moreover, since its streamlined four-layer protocol stack and higher data-communication efficiency reduce protocol and processing overhead relative to the Ethernet-based RoCE stack, Co-Fabric cuts the cost and power of the interconnect itself by up to 80% and 5%, respectively. These results demonstrate Co-Fabric's advantage for AI computing centers.

cs.DC↗
arXiv2026

Hydrozoan: Latency-Adaptive DAG Consensus under Mixed Byzantine and Crash Faults

DAG-based consensus protocols can achieve great throughput and the optimal three-message-delay limit for n = 3f+1 consensus. While two-delay protocols exist, they pay with reduced resilience (requiring 5f+1-style committees) or rely on fallbacks that sacrifice the DAG's high throughput. This paper introduces Hydrozoan, the first DAG protocol with a dual commit path under a hybrid fault model of f Byzantine and c crashed validators, on n = 3f+c+2p+1 validators. Leaders commit in two message delays whenever at most p validators are faulty, and in three otherwise, with no extra messages, no view changes, and multiple leaders per round. Both paths are evaluated on the same DAG, using a novel graded indirect rule to reconcile them so that every honest validator reaches the same decision. We show that under geo-distributed conditions, which path is faster is a property of geography rather than the protocol, as rounds reaching a remote region cost far more than those that do not. The (f, c, p) knobs place the fast quorum where the deployment requires it, allowing a commit in two message delays. If misconfigured, Hydrozoan can still commit in three message delays: Hydrozoan commits on whichever path fires first. We also present Optimal-Hydrozoan, a variant that tolerates one more fault on the fast path, the first construction to match the known lower bound. The safety and liveness of both protocols are machine-checked in Lean 4. Our geo-distributed evaluation shows that Hydrozoan matches Mysticeti's throughput, commits ~25% faster when the fast quorum fits fast regions, and falls back to three message delays when it does not or past p faults, where existing two-delay protocols stall.

cs.DC↗
arXiv2026

Reforge: Low-Latency Distributed GNN Serving with Selective Embedding Recomputation

Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However, serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads of constructing and executing computation graphs, which represent information flow across large neighborhoods. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. To this end, we propose Reforge, a system that enables low-latency GNN serving for large graphs with minimal accuracy loss through two key ideas. First, Reforge employs selective recomputation of precomputed embeddings, which allows for reusing precomputed computation subgraphs while selectively recomputing a small fraction to minimize accuracy loss. Second, we develop computation graph parallelism, which reduces communication overhead by parallelizing the creation and execution of computation graphs across machines. Our evaluation with large graph datasets and GNN models shows that Reforge significantly outperforms state-of-the-art techniques.

cs.DC↗