Ray-2.58.0
UpdateUnverifiedAdded Sep 24, 2026
Highlights Ray Serve LLM: In this release we've completed KV cache and token aware request routing, which was previewed in 2.57. Tokenization now happens in-process on the LLMRouter ingress replica, the routing decision is made there, tokens are transmitted out-of-band so the engine does not re-tokenize, KV lifecycle events are broadcast to every ingress...
Topics: AI agents, LLMs, Governance, Data integration, BI
More Ray releases
Every Ray release| Date | Release | Type |
|---|---|---|
| Aug 12 | Ray-2.57.0unverified Update | Update |
| Aug 12 | Ray-2.56.1unverified Update | Update |
| Jun 29 | Ray-2.56.0unverified Update | Update |
| Apr 22 | Ray-2.55.1unverified Update | Update |
| Apr 15 | Ray-2.55.0unverified Update | Update |
| Mar 25 | Ray-2.54.1unverified Update | Update |
| Feb 19 | Ray-2.54.0unverified Update | Update |
| Dec 20 | Ray-2.53.0unverified Update | Update |
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.