LearnedCache shows a quantized one-layer perceptron, trained on eBPF kernel traces and deployed through cache_ext, can beat FIFO page-cache eviction on some Filebench workloads.
A learned cache eviction framework with mini- mal overhead
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
SCION is a lightweight orchestration layer that picks among six deployable cache policies via an offline-trained linear selector on short-prefix size and reuse fingerprints, improving cacheable miss ratio over SIEVE on most of 30 traces while staying near the best expert.
Learning-augmented LRU achieves 1-consistency and O(k)-robustness for GPU caching with low overhead, implemented in LCR to cut P99 TTFT by up to 28.3% on LLM workloads and raise throughput by up to 24.2% on DLRM workloads.
citing papers explorer
-
LearnedCache: eBPF-Integrated Perceptron-Based Eviction Policies for the Linux Page Cache
LearnedCache shows a quantized one-layer perceptron, trained on eBPF kernel traces and deployed through cache_ext, can beat FIFO page-cache eviction on some Filebench workloads.
-
SCION: Size-aware Policy Orchestration for Nonstationary Object Caches (Long Paper Version)
SCION is a lightweight orchestration layer that picks among six deployable cache policies via an offline-trained linear selector on short-prefix size and reuse fingerprints, improving cacheable miss ratio over SIEVE on most of 30 traces while staying near the best expert.
-
Toward Robust and Efficient ML-Based GPU Caching for Modern Inference
Learning-augmented LRU achieves 1-consistency and O(k)-robustness for GPU caching with low overhead, implemented in LCR to cut P99 TTFT by up to 28.3% on LLM workloads and raise throughput by up to 24.2% on DLRM workloads.