OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity
56,020 Commits 8,304 Branches 150 Tags 1.5 GiB
3888555fa1
Commit Graph

5 Commits

Author SHA1 Message Date
Nikita Vedeneev
46f16b9363 Improve bsr @ strided performance in baddmm for bfloat16/half with Triton kernels. (#88078) 
As per title.

Additionally we also introduce support for:
- Rectangular block sizes which are powers of 2 and at least 16 (triton's `dot` limitation).
- Batch support with broadcasting for either of the arguments.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/88078
Approved by: https://github.com/cpuhrsch
 2023-01-26 07:58:27 +00:00
PyTorch MergeBot
60bf851931 Revert "Improve bsr @ strided performance in baddmm for bfloat16/half with Triton kernels. (#88078)" 
This reverts commit 8383b5c488.

Reverted https://github.com/pytorch/pytorch/pull/88078 on behalf of https://github.com/malfet due to This seems to have broke sm_86 testing, see https://hud.pytorch.org/hud/pytorch/pytorch/master/1?per_page=50&name_filter=sm86%20%2F%20test%20(default%2C%203
 2023-01-19 23:37:59 +00:00
Nikita Vedeneev
8383b5c488 Improve bsr @ strided performance in baddmm for bfloat16/half with Triton kernels. (#88078) 
As per title.

Additionally we also introduce support for:
- Rectangular block sizes which are powers of 2 and at least 16 (triton's `dot` limitation).
- Batch support with broadcasting for either of the arguments.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/88078
Approved by: https://github.com/cpuhrsch
 2023-01-19 03:14:54 +00:00
PyTorch MergeBot
89f1ad08b4 Revert "Improve bsr @ strided performance in baddmm for bfloat16/half with Triton kernels. (#88078)" 
This reverts commit 7f256fff77.

Reverted https://github.com/pytorch/pytorch/pull/88078 on behalf of https://github.com/huydhn due to This breaks lint 7f256fff77
 2023-01-17 22:14:37 +00:00
Nikita Vedeneev
7f256fff77 Improve bsr @ strided performance in baddmm for bfloat16/half with Triton kernels. (#88078) 
As per title.

Additionally we also introduce support for:
- Rectangular block sizes which are powers of 2 and at least 16 (triton's `dot` limitation).
- Batch support with broadcasting for either of the arguments.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/88078
Approved by: https://github.com/cpuhrsch
 2023-01-17 21:43:20 +00:00