EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Delete redundant codes related to communication (#2717)

Browse Source 
### What this PR does / why we need it?
Delete redundant codes related to communication

### Does this PR introduce _any_ user-facing change?
not involve

### How was this patch tested?
not involve

- vLLM version: v0.10.1.1
- vLLM main:
6c7af8110a

---------

Signed-off-by: 刘哲续 <liuzhexu1@huawei.com>
Co-authored-by: 刘哲续 <liuzhexu1@huawei.com>
This commit is contained in:
henryxuxu0716
2025-09-05 09:39:39 +08:00
committed by GitHub
parent 5b3646ab21
commit 51a2aec115
6 changed files with 7 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/ut/ops/test_fused_ops.py
View File

@@ -139,7 +139,6 @@ def mock_dist_env(mocker: MockerFixture):
patch('torch.distributed.all_gather'), \
patch('torch.distributed.all_to_all_single'), \
patch('vllm_ascend.ops.fused_moe.tensor_model_parallel_all_reduce'), \
patch('vllm_ascend.ops.fused_moe.data_parallel_reduce_scatter'), \
patch('vllm.model_executor.layers.fused_moe.config.get_dp_group',
return_value=mock_dp_and_tp_group(mocker)), \
patch('vllm_ascend.ops.fused_moe.get_ascend_config',

2
tests/ut/torchair/ops/test_torchair_fused_moe.py
View File

@@ -66,8 +66,6 @@ def mock_dist_env(mocker: MockerFixture):
patch('torch.distributed.all_to_all_single', return_value=torch.randn(8, 32)), \
patch('vllm_ascend.torchair.ops.torchair_fused_moe.tensor_model_parallel_all_reduce',
return_value=torch.randn(5, 32)), \
patch('vllm_ascend.torchair.ops.torchair_fused_moe.data_parallel_reduce_scatter',
return_value=torch.randn(5, 32)), \
patch('vllm.model_executor.layers.fused_moe.config.get_dp_group',
return_value=mock_dp_and_tp_group(mocker)), \
patch('vllm_ascend.torchair.ops.torchair_fused_moe.get_ascend_config',