High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLang.
novitalabs/pegaflow is sitting at #830 on the trending leaderboard with a pulse of 11/100 with no cross-source channels firing yet — GitHub-stars-only signal so far.
It sits at 116 stars without a fresh weekly delta on record — the trending placement here is steady-state interest in the AI agent / LLM tooling stack rather than a 7-day breakout.
Watch-outs: no tagged release on record (treat as pre-stable), the maintainer graph is thin — 1 contributors carrying it.
//COMMENTS · 0
Sign in to join the discussion
Sign in