-
Notifications
You must be signed in to change notification settings - Fork 399
move float8 blockwise kernels out of prototype #3256
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3256
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
| triton = pytest.importorskip("triton", reason="Triton required to run this test") | ||
|
|
||
| from torchao.prototype.blockwise_fp8_inference.blockwise_quantization import ( | ||
| from torchao.kernel.blockwise_quantization import ( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
note for later: let's rename this torchao.kernels* (plural)
* Update [ghstack-poisoned] * Update [ghstack-poisoned] * Update [ghstack-poisoned]
Summary:
These will be useful as a fallback path for a_1_128_w_128_128 (DeepSeek)
scaling support for float8 inference. Bringing out of prototype folder.
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: