Skip to content
#

inference-latency

Star

Here are 2 public repositories matching this topic...

Language: All
Filter by language
All 2 Jupyter Notebook 1 Rust 1

david-spies / ghostcacher

Star 0

GhostCacher is a distributed Key-Value (KV) prompt caching orchestrator that dramatically reduces LLM inference latency and cost by storing and reusing the computed attention states of frequently used prompt prefixes across a distributed GPU cluster.

python rust redis dockerfile typescript key-value prometheus grafana-dashboard orchestrator prompt-caching llm-inference inference-latency prompt-prefixes distributed-key-value-caching
  • Updated Apr 30, 2026
  • Rust

Improve this page

Add a description, image, and links to the inference-latency topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

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

Learn more