[xnn update prep] deprecate sdpa #11506
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11506
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 425ca7e with merge base 5ef38d3 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
| @@ -2097,7 +2061,6 @@ DefineNodeFunc getDefineNodeFunc(fb_xnnpack::XNodeUnion nodeType) { | |||
| _DEFINE(Concatenate4) | |||
| _DEFINE(Concatenate5) | |||
| _DEFINE(StaticSlice) | |||
| _DEFINE(ScaledDotProductAttention) | |||
There was a problem hiding this comment.
Not updating schema for marking deprecated? XNNScaledDotProductAttention
There was a problem hiding this comment.
so XNNPACK removed the operator from their codebase, so for next update we need to delete. I can mark the operator in the schema as deprecated though.
| @@ -1,111 +0,0 @@ | |||
| # Copyright (c) Meta Platforms, Inc. and affiliates. | |||
There was a problem hiding this comment.
Should we continue partitioning this and lower it as decomposed?
Else this will be a BC breaking change.
There was a problem hiding this comment.
So ever since my new partitioner, SDPA has not been delegated. I assumed that no models in production or since h ave really used any sdpa implementation (also because i heard our sdpa is slow). so I believe this is safe to remove. I can import it internally to make sure
No description provided.