# Vllm

> Markdown twin of https://web-production-180a9.up.railway.app/companies/vllm · https://web-production-180a9.up.railway.app/companies/vllm.md

## On shared sources

- [AMD](https://web-production-180a9.up.railway.app/companies/amd) (2)

## Pulse

- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2095744598073053470)
  On total tokens per $ TCO, a new AMD MI355x submission beats B300 at lower interactivity ranges on AgentX. Shoutout to vLLM, AMD, and LMCache engineers. https://t.co/1oYYeYYu9S
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2095731112207061029)
  On total tokens per $ TCO, a new AMD MI355x submission beats B300 at lower interactivity ranges on AgentX. Both high throughput configs use disaggregated setups. Shoutout to vLLM, AMD, and LMCache eng…

---

Source: Robotics insights · https://web-production-180a9.up.railway.app/companies/vllm.md