add more options for loading checkpoints #5823
Closed
Conversation
This file contains hidden or 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
This PR adds support to load qat_lora checkpoints. It mainly does the following two things: - Refactor the existing quantization flow for SpinQuant to be separate function, which is used to load QAT checkpoint as well since they share the same format. - For QAT_LoRA checkpoint, we do one more extra step after quantization. It replaces `Int8DynActInt4WeightLinear` layers with `Int8DynActInt4WeightLinearLoRA` which contains LoRA adaptor. Differential Revision: [D63714794](https://our.internmc.facebook.com/intern/diff/D63714794/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5823
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 96e6198 with merge base 152e22d ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D63714794 |
helunwencser
added a commit
that referenced
this pull request
Oct 2, 2024
This PR adds support to load qat_lora checkpoints. It mainly does the following two things: - Refactor the existing quantization flow for SpinQuant to be separate function, which is used to load QAT checkpoint as well since they share the same format. - For QAT_LoRA checkpoint, we do one more extra step after quantization. It replaces `Int8DynActInt4WeightLinear` layers with `Int8DynActInt4WeightLinearLoRA` which contains LoRA adaptor. Differential Revision: [D63714794](https://our.internmc.facebook.com/intern/diff/D63714794/) ghstack-source-id: 245945707 Pull Request resolved: #5823
This PR adds support to load qat_lora checkpoints. It mainly does the following two things: - Refactor the existing quantization flow for SpinQuant to be separate function, which is used to load QAT checkpoint as well since they share the same format. - For QAT_LoRA checkpoint, we do one more extra step after quantization. It replaces `Int8DynActInt4WeightLinear` layers with `Int8DynActInt4WeightLinearLoRA` which contains LoRA adaptor. Differential Revision: [D63714794](https://our.internmc.facebook.com/intern/diff/D63714794/) [ghstack-poisoned]
helunwencser
added a commit
that referenced
this pull request
Oct 2, 2024
Pull Request resolved: #5823 Internal: This PR adds support to load qat_lora checkpoints. It mainly does the following two things: - Refactor the existing quantization flow for SpinQuant to be separate function, which is used to load QAT checkpoint as well since they share the same format. - For QAT_LoRA checkpoint, we do one more extra step after quantization. It replaces `Int8DynActInt4WeightLinear` layers with `Int8DynActInt4WeightLinearLoRA` which contains LoRA adaptor. Differential Revision: [D63714794](https://our.internmc.facebook.com/intern/diff/D63714794/) ghstack-source-id: 245956347
|
This pull request was exported from Phabricator. Differential Revision: D63714794 |
helunwencser
changed the title
mergennachin
approved these changes
Oct 2, 2024
|
This pull request has been merged in 9ff3351. |
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Stack from ghstack (oldest at bottom):
Differential Revision: D63714794