Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.
Cache-aware orchestration for LLM agents. Fork helpers that share cached prefixes, detect cache breaks, and cut token costs by 38%+.
Arhitectura Sistemelor de Calcul - UPB 2020
DeepSeek缓存优化器 v1.1 — Reasonix四支柱 + 语义压缩 (命中率+30%)
Comparison of parallel matrix multiplication methods using OpenMP, focusing on cache efficiency, runtime, and performance analysis with Intel VTune.
University of Pittsburgh ECE 1175
Enhanced Learned Bloom Filter with cache optimization, incremental learning, and adaptive threshold control
Experiments on prompt-prefix stability, deterministic tool definitions, and cache hit rate for tool-using LLM agents
Mathematical optimization of multi-level cache allocation using calculus and Python — derives minimum memory access time through symbolic differentiation, numerical solving, and visualization.
Solved tasks of the master's degree courses of speciality "Algorithms and Systems for Big Data Processing".
An SRAM-optimized, mathematically exact, billion-scale MIPS vector database utilizing Fast Walsh-Hadamard Transforms and FP8 quantization bounds.
Add a description, image, and links to the cache-optimization topic page so that developers can more easily learn about it.
To associate your repository with the cache-optimization topic, visit your repo's landing page and select "manage topics."