OpenAI says its own models optimised Astra Ultrafast's inference on Nvidia GPUs

T2Covered by 1 source · first reported by UploadVR / Road to VR / MIXED at 04 Oct, 03:37 UTC

OpenAI used its own models to tune the inference software that serves GPT-6 Astra Ultrafast on Nvidia hardware, two of its executives say on the record in a post Nvidia published on October 1. "We used our internal models to optimize inference on NVIDIA GPUs, and NVIDIA's programmability helped us…

aihardwareiottelecomxr

Sources

• T2OpenAI says its own models optimised Astra Ultrafast's inference on Nvidia GPUsUploadVR / Road to VR / MIXED04 Oct, 03:37