Feng Liu e117b3d693 [Perf] vectorize PCP/DCP loops in mla_v1.py (#5003) ...

### What this PR does / why we need it?
- Replace nested PCP/DCP Python loops with fully vectorized tensor
operations

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: F.Liu <liufeng248@huawei.com>
Co-authored-by: F.Liu <liufeng248@huawei.com>

2025-12-22 11:06:30 +08:00

..

e2e

[Performance] Add async exponential while model executing (#4501)

2025-12-20 21:23:21 +08:00

ut

[Perf] vectorize PCP/DCP loops in mla_v1.py (#5003)

2025-12-22 11:06:30 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00