Move Uintx out of prototype for future extension #635
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/635
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit ec39e6c with merge base 433cd14 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
requested review from
andrewor14,
msaroufim,
jcaip,
HDCharles and
vayuda
vayuda
approved these changes
Aug 8, 2024
jerryzh168
force-pushed
the
move-intx
branch
2 times, most recently
from
bc7bff3
to
462e94e
Compare
vayuda
reviewed
Aug 9, 2024
msaroufim
approved these changes
Aug 12, 2024
There was a problem hiding this comment.
LG, mind also updating the README here https://github.com/pytorch/ao#community-contributions
Summary: Thanks @vayuda for adding the initial version of Uintx tensor subclass we can now integrate this with `torch.uint1` to `torch.uint7` dtypes with some helpers to unblock the benefit of bitpacking (model size saving) to people first, and then we can gradually optimize the performance. Also executorch is planning to integrate their low bit kernels with us, more native experience with these lower bit types will be required / useful there as well Test Plan: python test/dtypes/test_uintx.py Reviewers: Subscribers: Tasks: Tags:
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
Thanks @vayuda for adding the initial version of Uintx tensor subclass we can now integrate this with
torch.uint1totorch.uint7dtypes with some helpers to unblock the benefit of bitpacking (model size saving) to people first, and then we can gradually optimize the performance.Also executorch is planning to integrate their low bit kernels with us, more native experience with these lower bit types will be required / useful there as well
Test Plan:
python test/dtypes/test_uintx.py
Reviewers:
Subscribers:
Tasks:
Tags: