SGLang launches AWS Trainium plugin beta with inference and RL rollouts on Trainium2/3
ying11231 · x · 2026-10-23
SGLang announced the beta of its AWS Trainium plugin, built on TorchNeuron and running on Trainium2 and Trainium3 in close collaboration with AWS. The beta includes inference serving and RL rollouts, support for the Qwen3, DeepSeek, and GLM model families with more frontier models coming, and an early preview of heterogeneous RL with rollouts on Trainium and training via Miles (radixark). More details at next month's SGLang Summit—a notable step for open inference stacks beyond NVIDIA silicon.
More from Infra
- x87 floating point in 1995-2005 PC games murders ARM emulators — FEX's new stack optimization pass — lauriewired · 2026-10-23
- Video Model API Markups Exposed: Runway Charges 414%, New Sume API Launches With 0% Markup — Scobleizer · 2026-10-23
- Google Cloud launches Agent Compute Engine, a new VM type built for AI agents — testingcatalog · 2026-10-23
- LM Studio ships Read Aloud, powered by tiny local TTS model Phonon from Gradium — mattturck · 2026-10-23
- Lam Research system revenue up 35% QoQ as AI pushes 2027 WFE past $200B — BenBajarin · 2026-10-23
- Hugging Face Hub launches OpenUSD support with 2,500+ NVIDIA SimReady assets — mishig25 · 2026-10-23