Skip to content

Embedding quantization per backend #402

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 6 commits into from
Apr 23, 2024
Merged

Embedding quantization per backend #402

merged 6 commits into from
Apr 23, 2024

Conversation

mikekgfb
Copy link
Contributor

Embedding quantization per backend

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Meta Open Source bot. label Apr 23, 2024
malfet
malfet approved these changes Apr 23, 2024
View reviewed changes
Copy link
Contributor

@malfet malfet left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How do we test for anything like that?

@mikekgfb mikekgfb merged commit 052fb1a into main Apr 23, 2024
malfet added a commit that referenced this pull request Apr 23, 2024
@malfet
Revert "Embedding quantization per backend (#402)"
54309ec 
This reverts commit 052fb1a.
@malfet malfet mentioned this pull request Apr 23, 2024
Merged
malfet added a commit that referenced this pull request Apr 23, 2024
@malfet
Revert "Embedding quantization per backend (#402)" (#411)
8b35acd 
This reverts commit 052fb1a to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
mikekgfb added a commit that referenced this pull request Apr 23, 2024
@mikekgfb
Revert "Revert "Embedding quantization per backend (#402)" (#411)"
9508897 
This reverts commit 8b35acd.
mikekgfb added a commit that referenced this pull request Apr 23, 2024
@mikekgfb
Revert "Revert "Embedding quantization per backend"" (#415)
8d121ae 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
mikekgfb added a commit that referenced this pull request Apr 24, 2024
@mikekgfb
Merge lowering of gguf files with ET tests into pull.yml (#417)
2294882 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* merge GGUF tests into pull.yml
@malfet malfet deleted the embedding_quantization_per_backend branch April 30, 2024 16:51
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Embedding quantization per backend (#402)
634303a 
* ET or AOTI backend logic

* use args, not builder_args

* typo

* typo

* typo
malfet added a commit that referenced this pull request Jul 17, 2024
@malfet
Revert "Embedding quantization per backend (#402)" (#411)
cc5361c 
This reverts commit 052fb1a to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Revert "Revert "Embedding quantization per backend"" (#415)
f3cc50a 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Merge lowering of gguf files with ET tests into pull.yml (#417)
190e536 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* merge GGUF tests into pull.yml
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Embedding quantization per backend (#402)
d00bbf5 
* ET or AOTI backend logic

* use args, not builder_args

* typo

* typo

* typo
malfet added a commit that referenced this pull request Jul 17, 2024
@malfet
Revert "Embedding quantization per backend (#402)" (#411)
6678cb1 
This reverts commit 052fb1a to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Revert "Revert "Embedding quantization per backend"" (#415)
b310fea 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Merge lowering of gguf files with ET tests into pull.yml (#417)
38bc9f2 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* merge GGUF tests into pull.yml
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Embedding quantization per backend (#402)
57b7b63 
* ET or AOTI backend logic

* use args, not builder_args

* typo

* typo

* typo
malfet added a commit that referenced this pull request Jul 17, 2024
@malfet
Revert "Embedding quantization per backend (#402)" (#411)
71113cf 
This reverts commit 052fb1a to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Revert "Revert "Embedding quantization per backend"" (#415)
15efcfa 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Merge lowering of gguf files with ET tests into pull.yml (#417)
2ae2e8a 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* merge GGUF tests into pull.yml
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Embedding quantization per backend (#402)
c24f888 
* ET or AOTI backend logic

* use args, not builder_args

* typo

* typo

* typo
malfet added a commit that referenced this pull request Jul 17, 2024
@malfet
Revert "Embedding quantization per backend (#402)" (#411)
1f46052 
This reverts commit 052fb1a to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Revert "Revert "Embedding quantization per backend"" (#415)
b101af4 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Merge lowering of gguf files with ET tests into pull.yml (#417)
ecee04e 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* merge GGUF tests into pull.yml
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Embedding quantization per backend (#402)
7872b5a 
* ET or AOTI backend logic

* use args, not builder_args

* typo

* typo

* typo
malfet added a commit that referenced this pull request Jul 17, 2024
@malfet
Revert "Embedding quantization per backend (#402)" (#411)
426f405 
This reverts commit 052fb1a to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Revert "Revert "Embedding quantization per backend"" (#415)
971b1d0 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Merge lowering of gguf files with ET tests into pull.yml (#417)
458582a 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* merge GGUF tests into pull.yml
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Embedding quantization per backend (#402)
c204150 
* ET or AOTI backend logic

* use args, not builder_args

* typo

* typo

* typo
malfet added a commit that referenced this pull request Jul 17, 2024
@malfet
Revert "Embedding quantization per backend (#402)" (#411)
0f69590 
This reverts commit 052fb1a to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Revert "Revert "Embedding quantization per backend"" (#415)
46bad0e 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
malfet pushed a commit that referenced this pull request Jul 17, 2024
@mikekgfb @malfet
Merge lowering of gguf files with ET tests into pull.yml (#417)
a99dc12 
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acd.

* merge GGUF tests into pull.yml
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@malfet malfet malfet approved these changes

@metascroy metascroy metascroy approved these changes

@GregoryComer GregoryComer Awaiting requested review from GregoryComer

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Meta Open Source bot.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@mikekgfb @malfet @metascroy @facebook-github-bot