pytorch

mirror of https://github.com/saymrwulf/pytorch.git synced 2026-05-14 20:57:59 +00:00

History

chilli 237c4e6163 Improved flexattention bwd perf + added configurations for benchmarks (#129013 ) Before: <img width="519" alt="image" src="https://github.com/pytorch/pytorch/assets/6355099/6f4a9b37-4aff-48d3-aaba-7e8e5a5bf0fb"> After: <img width="541" alt="image" src="https://github.com/pytorch/pytorch/assets/6355099/423f179e-76f5-457b-8064-ee8a70247534"> After fixing strides: ![image](https://github.com/pytorch/pytorch/assets/6355099/58471587-404b-4bfc-b9b2-7546bdf53f54) Pull Request resolved: https://github.com/pytorch/pytorch/pull/129013 Approved by: https://github.com/drisspg, https://github.com/yanboliang ghstack dependencies: #128938		2024-06-21 15:58:53 +00:00
..
attention_bias_benchmarks.py	[5/N][Easy] fix typo for `usort` config in `pyproject.toml` (`kown` -> `known`): sort torch (#127126 )	2024-05-27 14:49:57 +00:00
better_transformer_vs_mha_functional.py	[5/N][Easy] fix typo for `usort` config in `pyproject.toml` (`kown` -> `known`): sort torch (#127126 )	2024-05-27 14:49:57 +00:00
score_mod.py	Improved flexattention bwd perf + added configurations for benchmarks (#129013 )	2024-06-21 15:58:53 +00:00
sdp.py	[5/N][Easy] fix typo for `usort` config in `pyproject.toml` (`kown` -> `known`): sort torch (#127126 )	2024-05-27 14:49:57 +00:00
sdpa.py	[5/N][Easy] fix typo for `usort` config in `pyproject.toml` (`kown` -> `known`): sort torch (#127126 )	2024-05-27 14:49:57 +00:00