Vmware, Inc.

Omnissa, LLC

Yuxin Kou

Yang Liu

Lin Lv

Yanchao Zhang

Tiejun Chen

Shreekanta Das

Hong Yue

Yinghua Chen

Techniques are described for redirecting GPU capability from a client device to the virtual desktop. The virtual desktop client includes a GPU controller deployed on the client computing device, which is capable of virtualizing the local GPU of the client device and exposing it to the virtual desktop. The virtual desktop agent operating on the host server includes a GPU consumer, which is capable of accepting machine learning (ML) or artificial intelligence (AI) workloads on the virtual desktop and offload these workloads to the GPU controller on the client computing device. When the GPU consumer detects the ML workload task on the virtual desktop, it transmits the ML workload task over the network to the GPU controller on the client computing device, which processes the ML workload task using the GPU of the client computing device and sends the results of the processing to the GPU consumer.

GPU capability redirection in virtual desktop environments

Disclosed are various examples of providing AI accelerator access as a service at the edge. In some embodiments an artificial intelligence (AI) accelerator device identifier is transmitted to register an AI accelerator with the AI broker service. An AI processing request for the AI accelerator is received from a networked computing device. A bus redirect of the AI accelerator to the networked device is enabled. An AI workload is performed controlled by the networked device through the bus redirect.

Edge AI accelerator service

Growing community of inventors

Beijing, China

Yuxin Kou