Topology-aware Preemptive Scheduling for Co-located LLM Workloads
| Autor: | Zhang, Ping, Su, Lei, Yang, Jinjie, Chen, Xin |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-location of batch jobs to fulfill resource valleys between successive peaks, and thus to saturate resource allocation in cluster-wide scope. These heterogeneous workloads often have different business priorities, and therefore preemption can be leveraged for resource elasticity. However, workloads often have distinct topology preferences as well. The resources released by lower-priority instances may fail to meet the requirements of high-priority online services which are usually latency-sensitive. The root cause behind such mis-match is a lack of topology awareness of resource scheduler, especially during preemption. To bridge this gap, we develop a fine-grained topology-aware method for preemptive scheduling of hybrid workloads. The method ensures that the resources freed by preempted tasks adhere to the topological affinity needs of high-priority preemptors in a guaranteed or best-effort manner. This dynamic alignment significantly increases the efficiency of preemption and improves overall scheduled performance for LLM workloads by $55\%$. Comment: 17 Pages, 11 Figures, 5 Tables |
| Databáze: | arXiv |
| Externí odkaz: |
|