EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

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

Browse Source 
### 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>
This commit is contained in:
Wang Yixuan
2025-12-08 19:22:14 +08:00
committed by GitHub
parent 6391f0625f
commit d412565ec9
15 changed files with 1736 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.pre-commit-config.yaml
View File

@@ -12,8 +12,8 @@ repos:
- id: codespell
args: [
--toml, pyproject.toml,
'--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/mla_preprocess/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
'-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND'
'--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
'-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND,ND'
]
additional_dependencies:
- tomli