A developer benchmarked Google's Gemma 4 E2B quantization-aware trained (QAT) checkpoint against the full bf16 release on a single NVIDIA L4 SageMaker endpoint, finding the 4-bit QAT model decodes at …
Amazon Web Services (AWS) announced new Ray capabilities on Amazon SageMaker HyperPod that integrate Ray with HyperPod's purpose-built infrastructure for foundation model training and serving. Data sc…
Amazon Web Services has added three new foundation models to its SageMaker JumpStart service, including Z.ai's GLM-5.2 FP8, NVIDIA's Nemotron-Nano-12B-v2, and Z.ai's GLM-OCR, targeting agentic enginee…
Amazon Web Services has integrated OpenAI's privacy-filter model into its SageMaker JumpStart hub, giving AWS customers a one-click deployment path for an enterprise-grade PII detection tool that iden…