Wang Yixuan d412565ec9 [Cherry-pick]bmm_transpose to v011dev (#3995) ...

### What this PR does / why we need it?
Add a custom op to acclerater the deepseek model. The fusion ops combine
the bmm and transpose together, which is applied to mla module.
Cherry-pick from this commtid c68ddc11ce53334fc9a17bad58342148cbf14e86

### Does this PR introduce _any_ user-facing change?
No

---------

Signed-off-by: hust17yixuan <303660421@qq.com>

2025-12-08 19:22:14 +08:00

..

__init__.py

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

test_batch_matmul_transpose.py

[Cherry-pick]bmm_transpose to v011dev (#3995)

2025-12-08 19:22:14 +08:00

test_bgmv_expand.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

test_bgmv_shrink.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

test_fused_moe.py

[refactor]support gatingtopk operator generalization (#4356)

2025-12-04 20:10:13 +08:00

test_gating_top_k_softmax.py

use npu_moe_gating_top_k_softmax (#1355)

2025-07-11 08:55:06 +08:00

test_mla_preprocess.py

remove redundant params in mla_preprocess kernel (#3530)

2025-10-21 19:20:13 +08:00

test_rotary_embedding.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

test_vocabparallelembedding.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00