-
Notifications
You must be signed in to change notification settings - Fork 24.9k
[pt2e][xnnpack_quantizer] add util function to convert scalars to attrs #110427
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Jerry provided a notebook solution for converting scalars to attrs so that they may be properly quantized: https://fburl.com/anp/kzz7tfn1 Adding this pass as a util function in xnnpack_quantizer_utils.py Differential Revision: [D49850150](https://our.internmc.facebook.com/intern/diff/D49850150/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/110427
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 480549b with merge base b083058 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
…lars to attrs" Jerry provided a notebook solution for converting scalars to attrs so that they may be properly quantized: https://fburl.com/anp/kzz7tfn1 Adding this pass as a util function in xnnpack_quantizer_utils.py Differential Revision: [D49850150](https://our.internmc.facebook.com/intern/diff/D49850150/) [ghstack-poisoned]
please make sure to fix lint before landing |
…lars to attrs" Jerry provided a notebook solution for converting scalars to attrs so that they may be properly quantized: https://fburl.com/anp/kzz7tfn1 Adding this pass as a util function in xnnpack_quantizer_utils.py Differential Revision: [D49850150](https://our.internmc.facebook.com/intern/diff/D49850150/) [ghstack-poisoned]
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
Adding "mul" to list of partitions that are supported by the quantizer. This shows up in EDSR, where we still want to quantize the mul op Differential Revision: [D49850151](https://our.internmc.facebook.com/intern/diff/D49850151/) Pull Request resolved: #110428 Approved by: https://github.com/jerryzh168 ghstack dependencies: #110427
Can't merge closed PR #110427 |
Stack from ghstack (oldest at bottom):
Jerry provided a notebook solution for converting scalars to attrs so that they may be properly quantized:
https://fburl.com/anp/kzz7tfn1
Adding this pass as a util function in xnnpack_quantizer_utils.py
Differential Revision: D49850150