master

Wwanggangguofeat(arch35): port causal_conv1d_bwd and layer_norm_gated_bwd kernels from flash-linear-attention into mindspeed_ops/arch35/triton/, add API wrappers with arch routing, and create ATK backward-only test suites for both operators

e6174ef4创建于 4 天前历史提交

文件	最后提交记录	最后更新时间
aclnn	feat: add aclnn ops of add Co-authored-by: shiyuan680<yangcheng104@huawei.com> # message auto-generated for no-merge-commit merge: !37 merge ascendc into master feat: add aclnn ops of add Created-by: zhizaidicengshehua Commit-by: shiyuan680 Merged-by: ascend-robot Description: ## What this PR does / why we need it? add aclnn ops of add. issue: [#30](https://gitcode.com/Ascend/MindSpeed-Ops/issues/30) ## Does this PR introduce any user-facing change? Please describe whether the PR will result in any user-facing usage changes. If there is related documentation, please specify its path. ## How was this patch tested? because of its demo of aclnn, so not support atk tests  See merge request: Ascend/MindSpeed-Ops!37	9 天前
tilelang	feat/fix/docs/style/refactor/adaptor/chore/test(backend): refactor Table of Contents Co-authored-by: shiyuan680<yangcheng104@huawei.com>	1 个月前
triton	feat(arch35): port causal_conv1d_bwd and layer_norm_gated_bwd kernels from flash-linear-attention into mindspeed_ops/arch35/triton/, add API wrappers with arch routing, and create ATK backward-only test suites for both operators	4 天前
__init__.py	feat/fix/docs/style/refactor/adaptor/chore/test(backend): refactor Table of Contents Co-authored-by: shiyuan680<yangcheng104@huawei.com>	1 个月前