#artificial intelligence
Aug 2025
LLM Serving Optimization with Variable Prefill and Decode Lengths
Sorted-F, which repeatedly selects feasible batches using an F-metric that balances batch cardinality against downstream decode cost, achieves a constant-factor approximation guarantee in the unit-time, uninterrupted-decoding model with known output lengths.
Meixuan Wang, Yinyu Ye, Zijie Zhou
· arXiv.org · 16 citations
· ⚡2