whx 96b2cdf6d8 [Ops][Triton] Add a triton kernel supporting partial rope. (#4413) ...

### What this PR does / why we need it?
This PR adds a triton rope kernel witch supports scenarios of `rope_dim
!= head_dim`. This can save the split op before rope and the concat op
after rope. Profiling shows improvement.

### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
I will add related ut after ci integrated with triton.


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>

2025-12-02 17:10:19 +08:00

..

__init__.py

[Core] Make V1 work and enable V1 engine test (#389)

2025-03-28 19:34:23 +08:00

attention_mask.py

[Bugfix] Fix model run _npu_flash_attention hang issue (#4410)

2025-11-29 09:20:22 +08:00

attention_v1.py

[Refactor] Remove redundant attention operator branches. (#4531)

2025-12-02 09:13:26 +08:00

mla_v1.py

[Feat] shared expert dp for deepseek_mtp (#3811)

2025-12-01 20:44:11 +08:00

sfa_v1.py

[Ops][Triton] Add a triton kernel supporting partial rope. (#4413)

2025-12-02 17:10:19 +08:00

utils.py

support FULL graph mode for GQA (#3970)

2025-11-17 10:50:35 +08:00