Trinary2 dtype and quantization for Bitnet 1.58 #285
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/285
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
Hi @CoffeeVampir3! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
facebook-github-bot
added
the
CLA Signed
|
Closing this in favor of #291 |
Motivated from issue #281 (comment)
This is initial groundwork for Bitnet 1.58. After some reflection, I think it's beneficial to view this as a distinct type different than a uint2 or regular packed structure, as there's some additional logistics involved in shifting/unshifting the distribution to maintain an optimal packing.