wangxiyuan 343955c7ac [CI] Follow vLLM FusedMoEParallelConfig interface change and clean up unused config (#1625) ...

This commit
78fe77534b
from vllm reverted the change for FusedMoEParallelConfig

This PR do the same to fix the CI error

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

2025-07-04 17:54:33 +08:00

..

attention

Fix W8A8 fused moe bug (#1529)

2025-07-02 16:40:51 +08:00

distributed

add ut for kv tansfer module (#1531)

2025-07-02 16:14:52 +08:00

fake_weight

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

ops

[CORE]initial support for torchair with non-mla backend (#1506)

2025-07-03 22:21:42 +08:00

patch/worker/patch_common

[CI] Fix FusedMoEConfig and input batch failure to recover CI (#1602)

2025-07-03 18:36:17 +08:00

quantization

[CORE]initial support for torchair with non-mla backend (#1506)

2025-07-03 22:21:42 +08:00

worker

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

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

base.py

[Build] Add build info (#1386)

2025-06-27 09:14:43 +08:00

test_ascend_config.py

[CI] Follow vLLM FusedMoEParallelConfig interface change and clean up unused config (#1625)

2025-07-04 17:54:33 +08:00

test_platform.py

[CORE]initial support for torchair with non-mla backend (#1506)

2025-07-03 22:21:42 +08:00

test_utils.py

[Quantization]300I Duo support w8a8 quantization (#1560)

2025-07-03 22:12:46 +08:00