Export Mimi to xnnpack #9303
Export Mimi to xnnpack #9303
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9303
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 1 Unrelated FailureAs of commit fa99b25 with merge base fc6d86e ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
iseeyuan
force-pushed
the
mimi_xnn
branch
2 times, most recently
from
3acdfba to
26a9cce
Compare
|
@iseeyuan has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
1 similar comment
|
@iseeyuan has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
|
@pytorchbot label "topic: not user facing" |
|
@iseeyuan has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
| @@ -131,6 +145,34 @@ def forward(self, x): | |||
| ep_decode_output = exported_decode.module()(input) | |||
| self.assertTrue(torch.allclose(ep_decode_output, ref_decode_output, atol=1e-6)) | |||
|
|
|||
| # PT2E Quantization | |||
| quantizer = XNNPACKQuantizer() | |||
| # 8 bit by default | |||
There was a problem hiding this comment.
Why not lower bit? Also how did you decide between pt2e and ao?
There was a problem hiding this comment.
One step for now. Will add 4 bit via 8da4w.
|
@iseeyuan has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
| f"chmod +x ./qnn_executor_runner &&", | ||
| "chmod +x ./qnn_executor_runner &&", |
There was a problem hiding this comment.
probably because of the lint runner I forgot to fix...
There was a problem hiding this comment.
Yeah I saw this on my prs and just bypassed it 😅
There was a problem hiding this comment.
Yeah lint runner failed on it.
|
@iseeyuan has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Differential Revision: D71430426 Pull Request resolved: pytorch#9303
Summary
[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.
[PLEASE REMOVE] If this PR closes an issue, please add a
Fixes #<issue-id>line.[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.
Test plan