Startup Buzz / New product
SGLang AWS Trainium plugin
by LMSYS Org
AILMSYS Org announces the beta of the SGLang AWS Trainium plugin, built on TorchNeuron and running on Trainium2 and Trainium3. The beta covers inference serving and RL rollouts for Qwen3, DeepSeek, and GLM model families, with an early preview of heterogeneous RL that runs rollouts on Trainium and training via Miles.
Why it matters: Runs SGLang inference serving and RL rollouts on Trainium2 and Trainium3, built on AWS's TorchNeuron backend
Original source
Open original ↗Recorded launch evidence
SGLang, in collaboration with AWS, announced the beta of its AWS Trainium plugin, which runs on Trainium2 and Trainium3 and is built on TorchNeuron.
Loading source…
Descriptions are prepared from the linked sources. Inclusion is not an endorsement.