SABER uses a fitted scalability curve and deadline-aware admission control to dynamically size continuous batches, improving SLA-compliant throughput by up to 26% over the best static configuration.
Fine tuning large language model for secure code generation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Adaptive Request Scheduling for CodeLLM Serving with SLA Guarantees
SABER uses a fitted scalability curve and deadline-aware admission control to dynamically size continuous batches, improving SLA-compliant throughput by up to 26% over the best static configuration.