26.0.0_core_r0.12.1

ascend-robotfix(torch/cp): use sbnd format before all2all

ebe3245b创建于 2月28日历史提交

文件	最后提交记录	最后更新时间
dot_product_attention	fix(torch/cp): use sbnd format before all2all Co-authored-by: clc2025<chenlucong@huawei.com> # message auto-generated for no-merge-commit merge: !3282 merge fixbug_ulysses_tnd into master fix(torch/cp): use sbnd format before all2all Created-by: clc2025 Commit-by: clc2025 Merged-by: ascend-robot Description: fixbug for ulysses tnd See merge request: Ascend/MindSpeed!3282	3 个月前
__init__.py	add TEDotProductAttention for master Co-authored-by: wuweiqiang24<wuweiqiang11@huawei.com> # message auto-generated for no-merge-commit merge: !3058 merge add_te_dpa_master into master add TEDotProductAttention for master Created-by: wuweiqiang24 Commit-by: wuweiqiang24 Merged-by: ascend-robot Description: 1. add TEDotProductAttention 2. add flash attention backend 精度已对齐local DotProductAttention实现 https://wiki.huawei.com/domains/63703/wiki/220407/WIKI202511289199170 See merge request: Ascend/MindSpeed!3058	5 个月前