Skip to content
#

eviction

Here are 40 public repositories matching this topic...

understudy

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

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.

  • Updated Jul 14, 2026
  • Python

Add this topic to your repo

To associate your repository with the eviction topic, visit your repo's landing page and select "manage topics."

Learn more