4 篇博文 含有标签「release」

An application should not need a new integration every time the best model changes. Hermes gives it one stable model name, while vLLM Semantic Router chooses from a qualified pool, delivers the answer, and measures whether that choice helped.

Themis (v0.3) made routing stateful and inspectable. Hermes turns that foundation into a model system that can improve as models and workloads change.

982 commits · 130 contributors · 107 first-time contributors since Themis. This is a milestone built by a growing community across models, runtime, evaluation, and the experience of putting it all to work.

AI is moving from generating answers to making decisions inside software.

Those decisions are everywhere: route an intent, gate an action by confidence, combine signals into a score, or ask many questions at once. Small decisions can shape the behavior of an entire system.

That vision is deeply aligned with vLLM Semantic Router: understand each request, apply policy, and choose what should happen next. It is why we invested in Decision 1.0: six open-weight Decision Foundation Models—and why we will keep improving them in the open.

Read the paper → · Explore the six models → · Try Decision Studio →

Today, we're excited to release Vela 1.0: 14 open models built for a world of many models.

Vela helps systems understand requests, protect sensitive information, find better context, and connect text, images, and audio. It is the model family we're building for vLLM Semantic Router, and a new foundation for everyone turning a collection of models into a capable system.

Explore all 14 models → · Try in Vela Studio →

As we approach the end of 2025, we're excited to share our Q4 2025 roadmap for vLLM Semantic Router. This quarter marks a significant milestone in our project's evolution as we prepare for our first major release: v0.1, codename "Iris", expected in late 2025 to early 2026.