A queueing model derives stability conditions for LLM inference services under combined compute and KV cache memory limits, with experimental validation showing typical deviations under 10%.
arXiv preprint arXiv:2402.16617 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
VPSG corrects predictable directional coordinate biases in MLLMs by shuffling visual positional encodings to isolate unconditioned tendencies and steering digit decoding with a lightweight finite-state machine, yielding accuracy gains on ScreenSpot-Pro without retraining.
citing papers explorer
-
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
A queueing model derives stability conditions for LLM inference services under combined compute and KV cache memory limits, with experimental validation showing typical deviations under 10%.
-
Mitigating Coordinate Prediction Bias from Positional Encoding Failures
VPSG corrects predictable directional coordinate biases in MLLMs by shuffling visual positional encodings to isolate unconditioned tendencies and steering digit decoding with a lightweight finite-state machine, yielding accuracy gains on ScreenSpot-Pro without retraining.