Best-effort high availability for single-replica Kubernetes workloads: no downtime from announced node disruptions (drains, upgrades, consolidation, spot reclaims) without a standing second replica.
-
Updated
Aug 25, 2026 - Go
Best-effort high availability for single-replica Kubernetes workloads: no downtime from announced node disruptions (drains, upgrades, consolidation, spot reclaims) without a standing second replica.
Gracefully evict Kubernetes Pods before they get OOM killed
A Time-aware Least Recently Used cache implementation in Go with configurable eviction policy
A high-performance, event-driven buffer library for Node.js and browsers, with configurable overflow strategies
"vcache" is a library that provides a concurrent-safe in-memory cache to store key-value pairs.
A LRU cache for memory paging and content caching.
Kubernetes operator: scale spare capacity ahead of voluntary node drains, then gate pods/eviction until Ready
DIY Form tools for MOTenantHelp including Eviction Defense Document Engine (EDDE)
Thread-safe, fixed-size, in-memory LRU cache that supports eviction, expiration, and out-of-band updates
A CPU cache-line hash table with zero-cost eviction. 64-byte buckets, LFU+LRU hybrid, 16-shard concurrency, per-entry TTL. 6.5-12x faster than moka on 4-thread workloads.
An Easy Java Cache Library
Generic in-memory cache with TTL and size-based eviction — TypeScript-first, zero dependencies.
High efficient embedded Cache library for Golang
70k+ evictions plotted with react-map-gl sourced from nyc open data
REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression
Custom CUDA kernels for KV-cache eviction + INT8 quantized paged attention (vLLM-oriented), PyTorch C++ extensions with Python API: eviction @16k blocks 1707.75us host -> 562us fused (~3x); INT8 attention p50 1.76-14.18ms; ~49.9% KV memory vs FP16; 26/26 pytest passing on T1000.
Cache optimization layer with intelligent eviction, warming, and invalidation strategies
Which Redis eviction policy keeps the most useful data, at what memory budget, for what shape of traffic - measured against Belady's optimal, the best any policy could have done
To associate your repository with the eviction topic, visit your repo's landing page and select "manage topics."