Make some fbgemm fp8 triton ops pt2 friendly #3188
Closed
Conversation
This file contains 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 pull request was exported from Phabricator. Differential Revision: D63560103 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
henrylhtsang
force-pushed
the
export-D63560103
branch
from
9544784
to
4f38802
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63560103 |
henrylhtsang
added a commit
to henrylhtsang/FBGEMM
that referenced
this pull request
Sep 29, 2024
Summary: X-link: facebookresearch/FBGEMM#283 Pull Request resolved: pytorch#3188 Make some fbgemm fp8 triton ops pt2 friendly.. # What this diff tries to do * stop using TensorWrapper and tl.reinterpret * Remove the use of triton_heuristics for _kernel_matmul_fp8_row # What this diff won't help: * triton_herustics use cases of EVEN_K. One option is to just merge that into the autotuning configs # need to do in the future: * Update other ops, like quantize_fp8_row. * Update documentation. Feels pretty outdated, and some still reference to TensorWrapper. Reviewed By: jwfromm Differential Revision: D63560103
|
This pull request was exported from Phabricator. Differential Revision: D63560103 |
henrylhtsang
added a commit
to henrylhtsang/FBGEMM
that referenced
this pull request
Sep 29, 2024
Summary: X-link: facebookresearch/FBGEMM#283 Pull Request resolved: pytorch#3188 Make some fbgemm fp8 triton ops pt2 friendly.. # What this diff tries to do * stop using TensorWrapper and tl.reinterpret * Remove the use of triton_heuristics for _kernel_matmul_fp8_row # What this diff won't help: * triton_herustics use cases of EVEN_K. One option is to just merge that into the autotuning configs # need to do in the future: * Update other ops, like quantize_fp8_row. * Update documentation. Feels pretty outdated, and some still reference to TensorWrapper. Reviewed By: jwfromm Differential Revision: D63560103
henrylhtsang
force-pushed
the
export-D63560103
branch
from
4f38802
to
c6b13bc
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63560103 |
henrylhtsang
pushed a commit
to henrylhtsang/FBGEMM
that referenced
this pull request
Sep 30, 2024
Summary: X-link: facebookresearch/FBGEMM#283 Pull Request resolved: pytorch#3188 Make some fbgemm fp8 triton ops pt2 friendly.. # What this diff tries to do * stop using TensorWrapper and tl.reinterpret * Remove the use of triton_heuristics for _kernel_matmul_fp8_row # What this diff won't help: * triton_herustics use cases of EVEN_K. One option is to just merge that into the autotuning configs # need to do in the future: * Update other ops, like quantize_fp8_row. * Update documentation. Feels pretty outdated, and some still reference to TensorWrapper. Differential Revision: D63560103
henrylhtsang
force-pushed
the
export-D63560103
branch
from
c6b13bc
to
259dd02
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63560103 |
henrylhtsang
pushed a commit
to henrylhtsang/FBGEMM
that referenced
this pull request
Sep 30, 2024
Summary: X-link: facebookresearch/FBGEMM#283 Pull Request resolved: pytorch#3188 Make some fbgemm fp8 triton ops pt2 friendly.. # What this diff tries to do * stop using TensorWrapper and tl.reinterpret * Remove the use of triton_heuristics for _kernel_matmul_fp8_row # What this diff won't help: * triton_herustics use cases of EVEN_K. One option is to just merge that into the autotuning configs # need to do in the future: * Update other ops, like quantize_fp8_row. * Update documentation. Feels pretty outdated, and some still reference to TensorWrapper. Differential Revision: D63560103
henrylhtsang
force-pushed
the
export-D63560103
branch
from
259dd02
to
0385aa4
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63560103 |
henrylhtsang
pushed a commit
to henrylhtsang/FBGEMM
that referenced
this pull request
Sep 30, 2024
Summary: X-link: facebookresearch/FBGEMM#283 Pull Request resolved: pytorch#3188 Make some fbgemm fp8 triton ops pt2 friendly.. # What this diff tries to do * stop using TensorWrapper and tl.reinterpret * Remove the use of triton_heuristics for _kernel_matmul_fp8_row # What this diff won't help: * triton_herustics use cases of EVEN_K. One option is to just merge that into the autotuning configs # need to do in the future: * Update other ops, like quantize_fp8_row. * Update documentation. Feels pretty outdated, and some still reference to TensorWrapper. Reviewed By: henrylhtsang Differential Revision: D63560103
henrylhtsang
force-pushed
the
export-D63560103
branch
from
0385aa4
to
63a4721
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63560103 |
henrylhtsang
force-pushed
the
export-D63560103
branch
from
63a4721
to
48569d0
Compare
henrylhtsang
pushed a commit
to henrylhtsang/FBGEMM
that referenced
this pull request
Sep 30, 2024
Summary: X-link: facebookresearch/FBGEMM#283 Pull Request resolved: pytorch#3188 Make some fbgemm fp8 triton ops pt2 friendly.. # What this diff tries to do * stop using TensorWrapper and tl.reinterpret * Remove the use of triton_heuristics for _kernel_matmul_fp8_row # What this diff won't help: * triton_herustics use cases of EVEN_K. One option is to just merge that into the autotuning configs # need to do in the future: * Update other ops, like quantize_fp8_row. * Update documentation. Feels pretty outdated, and some still reference to TensorWrapper. Reviewed By: henrylhtsang Differential Revision: D63560103
Summary: X-link: facebookresearch/FBGEMM#283 Pull Request resolved: pytorch#3188 Make some fbgemm fp8 triton ops pt2 friendly.. # What this diff tries to do * stop using TensorWrapper and tl.reinterpret * Remove the use of triton_heuristics for _kernel_matmul_fp8_row # What this diff won't help: * triton_herustics use cases of EVEN_K. One option is to just merge that into the autotuning configs # need to do in the future: * Update other ops, like quantize_fp8_row. * Update documentation. Feels pretty outdated, and some still reference to TensorWrapper. Reviewed By: henrylhtsang Differential Revision: D63560103
|
This pull request was exported from Phabricator. Differential Revision: D63560103 |
henrylhtsang
force-pushed
the
export-D63560103
branch
from
48569d0
to
be457d5
Compare
|
This pull request has been merged in d27acbd. |
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:
Make some fbgemm fp8 triton ops pt2 friendly..
What this diff tries to do
What this diff won't help:
need to do in the future:
Differential Revision: D63560103