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

[Refactor] [MoE] Rename moe-related classes & files (#3646)

Browse Source 
### What this PR does / why we need it?
1. Rename common_fused_moe.py to fused_moe.py.
2. Rename fused_moe_prepare_and_finalize.py / FusedMoEPrepareAndFinalize
to prepare_finalize.py / PrepareAndFinalize.
3. Rename vllm_ascend/ops/moe to vllm_ascend/ops/fused_moe.
4. Move vllm_ascend/ops/fused_moe.py to
vllm_ascend/ops/fused_moe/fused_moe.py
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut

- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
This commit is contained in:
weichen
2025-10-25 11:22:03 +08:00
committed by GitHub
parent 0637e8f021
commit 63c363d3de
25 changed files with 183 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/ut/models/conftest.py
View File

@@ -90,9 +90,9 @@ def mock_distributed():
mock_vllm_config.scheduler_config = Mock(max_num_seqs=256)
mock_vllm_config.model_config = Mock(max_model_len=2048, quant_config=None)
with patch("vllm_ascend.ops.common_fused_moe.get_current_vllm_config", return_value=mock_vllm_config), \
patch("vllm_ascend.ops.moe.token_dispatcher.torch.distributed.get_rank", return_value=0), \
patch("vllm_ascend.ops.moe.token_dispatcher.get_ascend_soc_version", return_value=None), \
with patch("vllm_ascend.ops.fused_moe.fused_moe.get_current_vllm_config", return_value=mock_vllm_config), \
patch("vllm_ascend.ops.fused_moe.token_dispatcher.torch.distributed.get_rank", return_value=0), \
patch("vllm_ascend.ops.fused_moe.token_dispatcher.get_ascend_soc_version", return_value=None), \
patch.dict("vllm.distributed.parallel_state.__dict__", _TP=tp_group, _EP=ep_group, _DP=dp_group,
_PP=pp_group), \
patch.dict("vllm_ascend.distributed.parallel_state.__dict__", _MC2=ep_group), \