# Radixark

> Markdown twin of https://roboterminal.app/companies/radixark · https://roboterminal.app/companies/radixark.md

## On shared sources

- [SemiAnalysis](https://roboterminal.app/companies/semianalysis) (2)
- [AMD](https://roboterminal.app/companies/amd) (1)
- [DeepSeek](https://roboterminal.app/companies/deepseek) (1)
- [Google](https://roboterminal.app/companies/google) (1)
- [Inferact](https://roboterminal.app/companies/inferact) (1)
- [MiniMax](https://roboterminal.app/companies/minimax) (1)
- [NVIDIA](https://roboterminal.app/companies/nvidia) (1)
- [Red Hat](https://roboterminal.app/companies/red-hat) (1)

## Pulse

- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2112347284713148746)
  ALERT🚨: SGLANG JUST MERGED MEGAKERNEL SUPPORT, GETTING CLOSE TO 1000 tok/s/user on the GB300 NVL72 AgentX Harness & increasing interactivity by 1.5x on MI355X too! Great work by the SGLang, RadixArk,…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2101355922148782264)
  Many Google TPU customers are already asking Google for SemiAnalysis AgentX performance results, as customers are saying that it is a representative workload of their agentic inference traffic. We are…

---

Source: Roboterminal · https://roboterminal.app/companies/radixark.md