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

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

Browse Source 
### What this PR does / why we need it?
1. Move additional functionalities from fused_moe.py to
common_fused_moe.py and remove fused_moe.py
2. Remove unnecessary custom classes from qwen3_moe.py, and it will be
completely removed after we release vllm-ascend v0.11.0

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?

Qwen3-30B-A3B/Qwen3-30B-A3B-W8A8/DeepSeek-V3-W4A8-Pruing/deepseek-mtp/pangu-pro-moe-pruing:

1. Enable/Disable EP
3. Aclgraph & eager
4. SP


- vLLM version: v0.11.0

---------

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
This commit is contained in:
weichen
2025-10-09 14:12:46 +08:00
committed by GitHub
parent a36e3da78e
commit 94dd832815
17 changed files with 175 additions and 1110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/ut/models/conftest.py
View File

@@ -96,7 +96,7 @@ def mock_distributed():
patch("vllm_ascend.models.deepseek_v2.get_pp_group", return_value=pp_group), \
patch("vllm_ascend.models.deepseek_v2.get_pp_group",
return_value=Mock(is_first_rank=False, is_last_rank=False)), \
patch("vllm_ascend.ops.fused_moe.get_current_vllm_config", return_value=mock_vllm_config), \
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), \
patch.dict("vllm.distributed.parallel_state.__dict__", _TP=tp_group, _EP=ep_group, _DP=dp_group,