wangxiyuan ba19dd3183 Revert PTA upgrade PR (#3352) ...

we notice that torch npu 0919 doesn't work. This PR revert related
change which rely on 0919 version.
Revert PR: #3295  #3205  #3102 

Related: #3353

- vLLM version: v0.11.0

2025-10-10 14:09:53 +08:00

..

expert_map.json

…

test_activation.py

…

test_comm_utils.py

Refactor tensor_parallel and comm_utils (#2814)

2025-09-11 21:26:36 +08:00

test_common_fused_moe.py

[Refactor] Adjustments to moe_comm_method selection process (#3001)

2025-09-22 19:12:58 +08:00

test_expert_load_balancer.py

…

test_fused_moe_prepare_and_finalize.py

[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)

2025-10-09 14:12:46 +08:00

test_fused_ops.py

[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)

2025-10-09 14:12:46 +08:00

test_layernorm.py

Revert PTA upgrade PR (#3352)

2025-10-10 14:09:53 +08:00

test_linear.py

[CI] Upgrade vLLM version (#3139)

2025-09-25 07:36:51 +08:00

test_moe_comm_method.py

[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)

2025-10-09 14:12:46 +08:00

test_rotary_embedding.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

test_token_dispatcher.py

[bugfix] Fix moe bug: allgather error. (#3279)

2025-09-30 18:45:09 +08:00

test_vocab_parallel_embedding.py

Fix VocabParallelEmbedding UT (#2722)

2025-09-18 19:54:01 +08:00