Michael Goin
Michael Goin
Hi @d-smit could you share a link to what this blob file format is like? ONNX is already a binary format so is it a matter of compression for you?...
Okay, thanks for pointing us to the right docs @d-smit . It looks like that OAK-D camera device uses a custom hardware accelerator called MyriadX VPU Processor. DeepSparse focuses on...
Closing this issue as it seems the hardware is proprietary to Intel. Feel free to respond or reopen if you have more questions, thanks!
Hi @fxmarty, really interesting find, thanks for investigating this. Quantized MobileBERT at batch size=1 is pretty lightweight in compute so it's possible using hyperthreads might pay off in multistream benchmarking....
Hi @ErfolgreichCharismatisch while we don't support native Windows usage, you can run deepsparse in [Windows Subsystem for Linux](https://learn.microsoft.com/en-us/windows/wsl/install) or a Linux virtual machine.
Hi @Tim-blo, 1.1.0 is out! We tested that your model shared above works on the nightly and release. Let us know how it works for you, thanks.
Hey @Tim-blo have you had the chance to try the engine since then? We're looking at Wav2Vec models as a whole and would be interested in hearing your process on...
@pgmpablo157321 Yes this has been resolved, closing now thanks
Hope the detail was helpful! Feel free to re-open if you have further questions, thanks
@AlpinDale we're going to fold in the new dequant kernels so you aren't stuck with gevm all the time during prefill. There does seem to be really long model loading...