wangxiyuan a054f0f4ca [CI] change to new ds model (#1513) ...

Previous, the DeepSeek V3 Pruning weight is not correct, the moe layer
is not tested. We update a new Pruning model to enable moe layer
compute.

This PR fix the CI to address the new weight.

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

2025-06-30 19:02:29 +08:00

..

e2e

[CI] change to new ds model (#1513)

2025-06-30 19:02:29 +08:00

ut

[V1][ModelRunner] Support pooling model for v1 engine (#1359)

2025-06-30 16:31:12 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

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

conftest.py

[V1][ModelRunner] Support pooling model for v1 engine (#1359)

2025-06-30 16:31:12 +08:00

model_utils.py

[CI] Refactor CI (#952)

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

utils.py

[V1][ModelRunner] Support pooling model for v1 engine (#1359)

2025-06-30 16:31:12 +08:00