NVIDIA and Google researchers have developed a host offloading technique in JAX that reduces high-bandwidth memory bottlenecks during LLM training, achieving up to 57% throughput improvements on NVIDI…
Amazon SageMaker AI now supports NVIDIA Blackwell GPUs with P6-B200 instances, enabling optimized training for large AI models through expanded memory and new precision formats. The integration allows…
Baseten has built the world's fastest API for GLM-5.2, achieving over 280 tokens per second as measured by Artificial Analysis. The performance is driven by optimizations including an updated inferenc…
Amazon Web Services announced a new method combining Amazon FSx for Lustre with NVIDIA GPUDirect Storage (GDS) to reduce large language model cold-start loading times from minutes to seconds on AWS GP…
NVIDIA and SchedMD have released a new topology/block plugin for Slurm 23.11 that enables topology-aware job scheduling on NVIDIA GB200 NVL72 systems, allowing workloads to be aligned with NVLink doma…