cccclai
cccclai
Oh would you prefer to use main branch or stable branch (release last October)
the doc for stable is: https://pytorch.org/executorch/stable/sdk-profiling.html for main is: https://pytorch.org/executorch/main/sdk-profiling.html
It's supposed to an aten core op. Probably this pull request can help https://github.com/pytorch/pytorch/pull/125789 - we're trying to land it
Before the PR is merged, workaround is calling these following ops manually. The same idea will be applied to https://github.com/pytorch/pytorch/pull/125789 ``` def decomp_linalg_vector_norm(a, order): # Compute the absolute values of...
> > Hi @cccclai , > > This PR is used to enable the model - dino_v2. May I know if you could help to check it, thank you! >...
this pr needs to be landed after the 4GB serialization pr.
Thanks for adding the pr. Really glad to have it enable llama models. A separate question, looks like we're using the source tranform from `-qmode 8da4w`. If apply this pr...
Closing stale PR
Closing stale PR