Add ability to pad the rowwise quantized tensors #4877
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 16, 2025
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
39b8f18 to
4baac07
Compare
yyetim
force-pushed
the
export-D82486197
branch
from
4baac07 to
6dc3e06
Compare
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 17, 2025
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: RandySheriff Differential Revision: D82486197
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 17, 2025
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: RandySheriff Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
6dc3e06 to
d5c866e
Compare
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 17, 2025
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: RandySheriff Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
d5c866e to
afe53e5
Compare
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 17, 2025
Summary: Pull Request resolved: pytorch#4877 X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: RandySheriff Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
afe53e5 to
2016dde
Compare
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 18, 2025
Summary: Pull Request resolved: pytorch#4877 X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: RandySheriff Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
2016dde to
91e714b
Compare
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 18, 2025
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: RandySheriff Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
91e714b to
02d93d5
Compare
yyetim
force-pushed
the
export-D82486197
branch
from
02d93d5 to
c42b948
Compare
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 18, 2025
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: RandySheriff Differential Revision: D82486197
yyetim
added a commit
to yyetim/FBGEMM-1
that referenced
this pull request
Sep 18, 2025
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: jwfromm, RandySheriff Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
c42b948 to
11492d8
Compare
Summary: X-link: facebookresearch/FBGEMM#1899 Some downstream kernels assume a certain width from quantized tensors. This adds the ability to do this as part of the triton fp8 quantize kernel. Reviewed By: jwfromm, RandySheriff Differential Revision: D82486197
yyetim
force-pushed
the
export-D82486197
branch
from
11492d8 to
9d2572e
Compare
|
This pull request has been merged in ac8ac3e. |
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:
X-link: https://github.com/facebookresearch/FBGEMM/pull/1899
Some downstream kernels assume a certain width from quantized tensors. This
adds the ability to do this as part of the triton fp8 quantize kernel.
Differential Revision: D82486197