AI at AMD

AMD engineer Chang Liu will be speaking at the vLLM Stockholm Meetup next week, alongside experts from @RedHat and AI Sweden, diving into production‑scale inference with vLLM through deep technical talks and live demos including inference optimization on @AMD GPUs. If you’re in Stockholm, don’t miss it. luma.com/q5aytn9u?tk=N1…

Save your spot to join the #AMDevs in SF🔽 amd.com/en/corporate/e…

See how @danielhanchen answered this at the last AMD AI DevDay, and join us April 30

Every system hits this trade off eventually. Precompute or lazy load?

Lots of talk about tokens lately, but what matters is how they show up in your workload. Let’s unpack the GTC benchmark. amd.com/en/developer/r…

🚀 @AMD just dropped a full guide: run OpenClaw🦞 for free on AMD Developer Cloud with Qwen3.5 + SGLang on a single MI300X! Following SGLang's support in @OpenClaw, here's a free way to get your own stack running: 🆓 $100 AMD Developer Cloud credits (~50 hrs of MI300X) 🧠 Qwen3.5-122B-A10B-FP8 served via SGLang in one Docker command 🔧 SGLang selectable natively in OpenClaw's onboarding CLI Your own self-hosted agent stack, on enterprise hardware, at zero cost. Happy building! 🫡 👉Blog link: amd.com/en/developer/r…

@curvedinf @AnushElangovan Thank you for being part of our community!

Received a really cool present in the mail this week from AMD for participating in their pytorch hackathon: an HP Zbook with Ryzen AI MAX 395 and 128 GB of RAM. Thank you @AnushElangovan and crew! I will bring more AMD support to my OSS projects with the laptop!

$ run agents --local Yes, you can run AI agents locally on Windows. This guide shows how to set up OpenClaw on AMD Ryzen AI Max+ systems or Radeon GPUs ↓↓

The wait is over. AMD is excited to launch the AI Developer Portal; a centralized hub designed for members of the AMD AI Developer Program. Whether you are prototyping on your local machine, training in the cloud, or scaling AI applications to production, the portal brings together the tools, learning resources, and community support you need to build faster. Get started: amd.com/en/developer/r…

Propelling Aerospace Innovation: Scaling Quantum Workflows on AMD GPUs With Rolls-Royce and Xanadu amd.com/en/developer/r…

Join the AMD Developer Discord to Ask the Experts all your questions about Lemonade! discord.com/invite/amd-dev

Catch up on the latest in the #AMDevs community below! 🧵

👀🦞

AMD AI DevDay 2026 brings together AMD engineers, technical leaders, ecosystem partners, open-source contributors, and AI developers. Happening April 30th, 2026 in San Francisco. Secure your spot today: amd.com/en/corporate/e…

Our next kernel competition is now open for submissions! A $1.1M cash prize competition sponsored by AMD on optimizing DeepSeek-R1-0528, GPT-OSS-120B on MI355X Registration: luma.com/cqq4mojz

Thanks for letting us know! If you're still running into issues with the access token, you can check our FAQ for help with account logins here: amd.com/en/registratio… If the issue continues, our customer support team can take a closer look and help you out: amd.com/en/forms/feedb…

@AIatAMD You dm is offf comment turned off as well.access code is not working

This week, the AMD Developer team has fresh new updates for you! Sweeps winners. RecSys Training. llm-d Meetup with RedHat AI, IBM Research and AMD. Inference scaling tutorial.

Join the GPU MODE Hackathon, sponsored by AMD, and push the boundaries of LLM inference performance on leading open models, optimized for AMD Instinct MI355X GPUs. Finalists will compete for the $1.1M total cash prize pool across two independent tracks, each focused on a specific model and inference stack. Learn more and get registered here: luma.com/cqq4mojz