The post names the hardware, supported model families, and beta scope, which helps readers gauge how far SGLang now reaches beyond GPUs.
Welcome AWS Trainium to the SGLang family!
Built on TorchNeuron, AWS’s native PyTorch backend, so SGLang’s model components and abstractions carried over largely intact. Our write-up covers what’s in the beta, why we built on TorchNeuron from day one, and our first end-to-end heterogeneous RL run.
Beta sign-up is in the blog!
Today, in close collaboration with @awscloud and alongside the TorchNeuron launch, we’re announcing the beta of the SGLang AWS Trainium plugin, built on TorchNeuron and running on Trainium2 and Trainium3. What’s in the beta: - Inference serving and RL rollouts - Support for Qwen3, DeepSeek, and GLM model families, with more frontier models on the way - Early preview of heterogeneous RL, with rollouts on Trainium and training via Miles (@radixark) Stay tuned for more at the SGLang Summit next month!
LMSYS Org · x.comPublished · added here
Original title: Welcome AWS Trainium to the SGLang family!
