top | item 41863883

(no title)

protastus | 1 year ago

Deploying a model on an NPU requires significant profile based optimization. Picking up a model that works fine on the CPU but hasn't been optimized for an NPU usually leads to disappointing results.

discuss

order

CAP_NET_ADMIN|1 year ago

Beauty of CPUs - they'll chew through whatever bs code you throw at them at a reasonable speed.

marginalia_nu|1 year ago

I don't think this is correct. The difference between well optimized code and unoptimized code on the CPU is frequently at least an order of magnitude performance.

Reason it doesn't seem that way is that the CPU is so fast we often bottleneck on I/O first. However, for compute-workloads like inference, it really does matter.

catgary|1 year ago

Yeah whenever I’ve spoken to people who work on stuff like IREE or OpenXLA they gave me the impression that understanding how to use those compilers/runtimes is an entire job.