The current version of TEN-VAD runs less efficiently on GPUs than it does on CPUs. This may be attributed to the fact that certain operators do not support GPU computation, resulting in a hybrid CPU/GPU processing mode.
Are there any plans to develop a pure-GPU version? This would be critically important for scenarios involving high-concurrency, multi-user detection.
The current version of TEN-VAD runs less efficiently on GPUs than it does on CPUs. This may be attributed to the fact that certain operators do not support GPU computation, resulting in a hybrid CPU/GPU processing mode.
Are there any plans to develop a pure-GPU version? This would be critically important for scenarios involving high-concurrency, multi-user detection.