fems14 ab5d110fcc vllm-ascend support chunked prefill (#1172) ...

### What this PR does / why we need it?
vllm-ascend support chunked prefill for MLA


---------

Signed-off-by: fems14 <1804143737@qq.com>

2025-06-14 22:31:16 +08:00

..

e2e

[CI] Fix PD job (#1129)

2025-06-09 16:34:41 +08:00

long_term

[Build] Move numba/quart to requirments and update DS baseline and sync graph typo fix (#1121)

2025-06-08 22:33:37 +08:00

multicard

[CI/UT][Graph] Add ut for torchair graph mode (#1103)

2025-06-14 16:59:00 +08:00

ops

add custom ascendc kernel vocabparallelembedding (#796)

2025-06-12 10:44:33 +08:00

singlecard

vllm-ascend support chunked prefill (#1172)

2025-06-14 22:31:16 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

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

conftest.py

[CI/UT][Graph] Add ut for torchair graph mode (#1103)

2025-06-14 16:59:00 +08:00

model_utils.py

[CI] Refactor CI (#952)

2025-05-28 06:31:35 +08:00

utils.py

[ModelRunner] Support embedding inputs (#916)

2025-06-06 20:21:13 +08:00