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

Add a CPU nbit to float dequantization op that supports torch.quintMxN type and QuantizedCPU backend #2995

Closed

excelle08 wants to merge 1 commit into pytorch:main from excelle08:export-D61305979

Contributor

excelle08 commented Aug 15, 2024

Summary: Add a CPU nbit to float dequantization operator torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat to support dequantization of int4 / int2 tensors which are of torch.quintMxN dtype and QuantizedCPU backend. This is to support D61305982

Differential Revision: D61305979

facebook-github-bot added the cla signed label

netlify bot commented Aug 15, 2024 •

edited

Loading

✅ Deploy Preview for pytorch-fbgemm-docs ready!

Name	Link
🔨 Latest commit	`ec37950`
🔍 Latest deploy log	https://app.netlify.com/sites/pytorch-fbgemm-docs/deploys/66c7a78f874f9d000899f66c
😎 Deploy Preview	https://deploy-preview-2995--pytorch-fbgemm-docs.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

Contributor

facebook-github-bot commented Aug 15, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

facebook-github-bot added the fb-exported label

Contributor

facebook-github-bot commented Aug 15, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

d7e035f

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 6882687 to d7e035f Compare

August 15, 2024 17:25

Contributor

facebook-github-bot commented Aug 15, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

a63245a

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from d7e035f to a63245a Compare

August 15, 2024 17:29

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

6b4e281

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Differential Revision: D61305979

Contributor

facebook-github-bot commented Aug 15, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from a63245a to 6b4e281 Compare

August 15, 2024 17:34

Contributor

facebook-github-bot commented Aug 15, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

b810052

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 6b4e281 to b810052 Compare

August 15, 2024 20:26

Contributor

facebook-github-bot commented Aug 17, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from b810052 to 663486b Compare

August 17, 2024 00:49

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

663486b

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

Contributor

facebook-github-bot commented Aug 18, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

30476dc

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 663486b to 30476dc Compare

August 18, 2024 05:06

Contributor

facebook-github-bot commented Aug 19, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

8c00180

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 30476dc to 8c00180 Compare

August 19, 2024 19:12

Contributor

facebook-github-bot commented Aug 19, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

8f6ed39

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 8c00180 to 8f6ed39 Compare

August 19, 2024 21:06

Contributor

facebook-github-bot commented Aug 20, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

9cbbd0e

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 8f6ed39 to 9cbbd0e Compare

August 20, 2024 15:45

Contributor

facebook-github-bot commented Aug 20, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

9053aae

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 9cbbd0e to 9053aae Compare

August 20, 2024 15:50

Contributor

facebook-github-bot commented Aug 20, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 9053aae to 7241e64 Compare

August 20, 2024 15:55

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

7241e64

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

Contributor

facebook-github-bot commented Aug 22, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

8b23144

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 7241e64 to 8b23144 Compare

August 22, 2024 02:43

Contributor

facebook-github-bot commented Aug 22, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

7e5c890

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 8b23144 to 7e5c890 Compare

August 22, 2024 20:50

Contributor

facebook-github-bot commented Aug 22, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 added a commit to excelle08/FBGEMM that referenced this pull request


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

1ecffe5

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 7e5c890 to 1ecffe5 Compare

August 22, 2024 20:56


          Add a CPU nbit to float dequantization op that supports torch.quintMx…

ec37950

…N type and QuantizedCPU backend (pytorch#2995)

Summary:
Pull Request resolved: pytorch#2995

X-link: facebookresearch/FBGEMM#87

Add a CPU nbit to float dequantization operator `torch.ops.fbgemm.FusedNBitRowwiseQuantizedSBHalfFrontToFloat` to support dequantization of int4 / int2 tensors which are of `torch.quintMxN` dtype and `QuantizedCPU` backend. This is to support D61305982

Reviewed By: sryap

Differential Revision: D61305979

Contributor

facebook-github-bot commented Aug 22, 2024

This pull request was exported from Phabricator. Differential Revision: D61305979

excelle08 force-pushed the export-D61305979 branch from 1ecffe5 to ec37950 Compare

August 22, 2024 21:03

facebook-github-bot closed this in

986e80c

facebook-github-bot added the Merged label

Contributor

facebook-github-bot commented Aug 23, 2024

This pull request has been merged in 986e80c.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

cla signed fb-exported Merged