nathanodle
nathanodle
@addf400
I'm having the same issue. Torch is trying to load a tensor on a 16GB card and I get RuntimeError: Native API failed. Native API returns: -6 (PI_ERROR_OUT_OF_HOST_MEMORY) -6 (PI_ERROR_OUT_OF_HOST_MEMORY)...
OK thanks. In that case you may want to update the readme?  Thanks for the response!
I have a version that is ANSI compliant, will try to get a repo setup for you to browse
> Which GPU did you run on? Sorry, I should have mentioned that. Arc 770, latest drivers on Ubuntu. Thank you very much for looking into this, I really appreciate...
Is there an eta for someone to look at this? Just curious as I have a project I'm trying to validate on ARC. Thanks!
Update, I have also tried this with an Intel I9-11900K CPU and A770 with the same result. The first attempt was using an AMD Threadripper. The code does not work...
Just a note, I have gotten bad results with every single model I've tried to use with XPU, it's not limited to this model. From my perspective, ARC has been...
Yes, that is the model. I don't have the input prompt in front of me right now but I will get it for you. Thank you very much for looking...
I can also confirm that vLLM running under Docker is no longer segfaulting on my system, thank you!