Pedro Cuenca 24b8b5cf5e `mps`: Alternative implementation for `repeat_interleave` (#766) ... * mps: alt. implementation for repeat_interleave * style * Bump mps version of PyTorch in the documentation. * Apply suggestions from code review Co-authored-by: Suraj Patil <surajp815@gmail.com> * Simplify: do not check for device. * style * Fix repeat dimensions: - The unconditional embeddings are always created from a single prompt. - I was shadowing the batch_size var. * Split long lines as suggested by Suraj. Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Suraj Patil <surajp815@gmail.com>		2022-10-11 20:30:09 +02:00
..
fp16.mdx	[Docs] Advertise fp16 instead of autocast (#740)	2022-10-05 22:20:53 +02:00
mps.mdx	`mps`: Alternative implementation for `repeat_interleave` (#766)	2022-10-11 20:30:09 +02:00
onnx.mdx	No more use_auth_token=True (#733)	2022-10-05 17:16:15 +02:00
open_vino.mdx	[Docs] Minor fixes in optimization section (#420)	2022-09-08 13:13:46 +02:00