OptiKIT combines automated quantization and SLO-driven serving-parameter tuning to more than double per-GPU throughput on some production workloads while preserving near full-precision accuracy.
Values are normalized per-GPU RPS (SLO- compliant)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
OptiKIT combines automated quantization and SLO-driven serving-parameter tuning to more than double per-GPU throughput on some production workloads while preserving near full-precision accuracy.