Amazon EC2
AWS shows multi-turn reinforcement learning on SageMaker AI with a Wordle agent
AWS has published a hands-on guide to Multi-Turn Reinforcement Learning (MTRL) on Amazon SageMaker AI, using Wordle to show how to train a model on multi-step agent…
Deepgram's Nova-3 on AWS Trainium2 processes 11, 70% more audio per dollar
Deepgram and the AWS Forward Deployed Engineering team have ported the Nova-3 speech-to-text model to AWS Trainium2, and report that the setup processed 11, 70 percent…
Push-based KV transfer in vLLM cuts TTFT up to 3x in AWS benchmark
AWS has contributed a push-based NIXL connector to vLLM that moves KV cache transfer coordination off the critical path in disaggregated prefill-decode inference. In…