A scheduling and deployment optimization system for LLM inference on heterogeneous GPU/NPU clusters that reports 33.6% to 122.5% throughput gains over round-robin in two small testbeds.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
High-Throughput LLM inference on Heterogeneous Clusters
A scheduling and deployment optimization system for LLM inference on heterogeneous GPU/NPU clusters that reports 33.6% to 122.5% throughput gains over round-robin in two small testbeds.