[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)
### 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:
@@ -67,12 +67,11 @@ class MoECommMethod(ABC):
|
||||
hidden_states: torch.Tensor,
|
||||
router_logits: torch.Tensor,
|
||||
enable_shared_expert_dp: bool = False,
|
||||
rm_router_logits: bool = False,
|
||||
replace_allreduce: bool = False,
|
||||
gate=None) -> tuple[torch.Tensor, torch.Tensor]:
|
||||
hidden_states, router_logits, mc2_mask = self.fused_moe_prepare_finalize.prepare(
|
||||
hidden_states, router_logits, enable_shared_expert_dp,
|
||||
rm_router_logits, replace_allreduce, gate)
|
||||
replace_allreduce, gate)
|
||||
self.mc2_mask = mc2_mask
|
||||
return hidden_states, router_logits
|
||||
|
||||
|
||||
Reference in New Issue
Block a user