Preshuffled BF16I4 Gemm Kernel #3913
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: D72270467 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Apr 2, 2025
Summary: X-link: facebookresearch/FBGEMM#1003 This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas. Differential Revision: D72270467
jwfromm
force-pushed
the
export-D72270467
branch
from
3260bd3 to
f4c60d4
Compare
|
This pull request was exported from Phabricator. Differential Revision: D72270467 |
jwfromm
force-pushed
the
export-D72270467
branch
from
f4c60d4 to
fc2e0a8
Compare
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Apr 2, 2025
Summary: X-link: facebookresearch/FBGEMM#1003 This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas. Notably, this preshuffle approach is 1.5-2X faster than the standard bf16i4 gemm for most shapes. Differential Revision: D72270467
|
This pull request was exported from Phabricator. Differential Revision: D72270467 |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Apr 2, 2025
Summary: X-link: facebookresearch/FBGEMM#1003 This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas. Notably, this preshuffle approach is 1.5-2X faster than the standard bf16i4 gemm for most shapes. Differential Revision: D72270467
jwfromm
force-pushed
the
export-D72270467
branch
from
fc2e0a8 to
38fb7bb
Compare
|
This pull request was exported from Phabricator. Differential Revision: D72270467 |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Apr 2, 2025
Summary: X-link: facebookresearch/FBGEMM#1003 This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas. Notably, this preshuffle approach is 1.5-2X faster than the standard bf16i4 gemm for most shapes. Compared to other mixed dtype kernels like marlin and machete, we see that this new kernel is probably the best average performer. {F1976677491} Reviewed By: jianyuh Differential Revision: D72270467
Summary: X-link: facebookresearch/FBGEMM#1003 This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas. Notably, this preshuffle approach is 1.5-2X faster than the standard bf16i4 gemm for most shapes. Compared to other mixed dtype kernels like marlin and machete, we see that this new kernel is probably the best average performer. {F1976677491} Reviewed By: jianyuh Differential Revision: D72270467
jwfromm
force-pushed
the
export-D72270467
branch
from
38fb7bb to
2ac7e7d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D72270467 |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
Apr 2, 2025
Summary: X-link: facebookresearch/FBGEMM#1003 This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas. Notably, this preshuffle approach is 1.5-2X faster than the standard bf16i4 gemm for most shapes. Compared to other mixed dtype kernels like marlin and machete, we see that this new kernel is probably the best average performer. {F1976677491} Reviewed By: jianyuh, jiawenliu64 Differential Revision: D72270467
|
This pull request has been merged in 8cbb32c. |
q10
pushed a commit
to q10/FBGEMM
that referenced
this pull request
Apr 10, 2025
Summary: Pull Request resolved: facebookresearch/FBGEMM#1003 X-link: pytorch#3913 This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas. Notably, this preshuffle approach is 1.5-2X faster than the standard bf16i4 gemm for most shapes. Compared to other mixed dtype kernels like marlin and machete, we see that this new kernel is probably the best average performer. {F1976677491} Reviewed By: jianyuh, jiawenliu64 Differential Revision: D72270467 fbshipit-source-id: 8426afd6587547083b8307f515cda49145939554
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: This diff adds a preshuffled BF16I4 mixed dtype kernel using cutlass. Performance is quite compelling and shows substantial speedups for some shapes compared to bf16 x bf16 gemm backed by cublas.
Differential Revision: D72270467