RadixArk
AI inference and training infrastructure
RadixArk is an infrastructure-first company building large-scale AI inference and training systems. It is the commercial entity behind SGLang, an open-source inference engine originally developed at UC Berkeley, and Miles, an enterprise-facing reinforcement learning framework for LLM and VLM post-training. The company offers hosted inference services built on top of its open-source tooling, targeting AI teams that need fast, cost-efficient model serving at scale.
Websites:
Current Valuation
as of January 21, 2026 (Source)
Funding Summary
No funding data available.
Key People
Core OSS Projects
Fast serving framework for large language models and vision language models, featuring RadixAttention for efficient KV cache reuse.
Enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Business Information
Category
AI InfrastructureIndustries
Technologies
Sectors
Licenses
Similar Companies
Socials and Communities
Cossmology Badge
COSS Weekly Newsletter
Stay up to date with the latest news, funding rounds, and announcements from the COSS universe.
Check out COSS Weekly on the web