A topology-aware preemption scheduler for co-located LLM workloads raises topology affinity hit rate from 44.5% to 100% in simulation, but the 55% performance improvement is inferred, not directly measured.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Topology-aware Preemptive Scheduling for Co-located LLM Workloads
A topology-aware preemption scheduler for co-located LLM workloads raises topology affinity hit rate from 44.5% to 100% in simulation, but the 55% performance improvement is inferred, not directly measured.