Is there a conversion for how well a NVIDIA RTX A6000 datasheet will perform compared to an NVIDIA RTX A5000 datasheet that gets 50 frames per second (fps) with a single-precision performance of 27.8 Teraflops (TFLOPS), RT Core performance 54.2 TFLOPS, and Tensor performance 222.2 TFLOPS?
It looks like an RTX A5000 is capable of half precision floating point 16 (fp16) and integer eight ( INT8). Where would I find the specifications to affirm this?
Request you to share the model, script, profiler, and performance output if not shared already so that we can help you better.
Alternatively, you can try running your model with trtexec command.
While measuring the model performance, make sure you consider the latency and throughput of the network inference, excluding the data pre and post-processing overhead.
Please refer to the below links for more details: