Kumar Deepak
Kumar Deepak
Suggest creating few Operator level tests and adding to https://github.com/nod-ai/SHARK-TestSuite/tree/main/e2eshark
Any work started on this?
Hello all, I wanted to follow up on this request. We would like to upstream AMD EPYC processor specific optimizations termed as ZenDNN to PyTorch. PyTorch 2.0 is fine. Should...
> Windows driver expects these values to actually be unique, it causes a problem if you try to create multiple hardware contexts for multiple xclbins.
Should we not actually generate a uuid / guid by making a call such as RPC_STATUS status = UuidCreate(&uuid);
[AMD Official Use Only - General] Thank you! From: Benoit Jacob ***@***.***> Sent: Wednesday, February 28, 2024 10:57 AM To: nod-ai/SHARK ***@***.***> Cc: Deepak, Kumar ***@***.***>; Mention ***@***.***> Subject: Re:...
@nithinsubbiah , is the plan to modify the MLIR by running a script for now to work around and keep this issue open for real fix?
Super good diagram, schedule and clearly called out tasks with target dates @monorimet !!
@aviator19941 the default should fix it now it seems, has anyone tried 70B in main branch and seen issues resolved?
@IanWood1 and @pdhirajkumarprasad is this issue resolved?