Published onOctober 10, 2022Case Study: MotiveproductHow ExaDeploy has helped Motive to save money and accelerate their development.Read more →
Published onSeptember 26, 2022Load 60 BERTs onto a single T4technicalUsing partial runners to load 60 BERTs onto a T4 with no prespecified colocation.Read more →
Published onSeptember 16, 2022Getting Rid of CPU-GPU Copies in TensorFlowtechnicalPassing inputs and outputs directly through GPU memory in TensorFlow.Read more →
Published onAugust 26, 2022Are GPUs Worth it for ML?productHow to get the best cost and latency on ML workloads from a mix of GPUs and CPUs.Read more →
Published onAugust 17, 2022ML Deployment: When the Big Problem is… Going BigproductDissecting the issues that pop up when trying to deploy an ML workload.Read more →