[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:
@@ -63,7 +63,7 @@ class TestMoECommMethod(TestBase):
|
||||
|
||||
# Verify prepare was called with correct arguments
|
||||
mock_pf_instance.prepare.assert_called_once_with(
|
||||
hidden_states, router_logits, False, False, False, None)
|
||||
hidden_states, router_logits, False, False, None)
|
||||
|
||||
# Test finalize method
|
||||
comm_impl.finalize(h_out, reduce_results=True)
|
||||
@@ -108,7 +108,7 @@ class TestMoECommMethod(TestBase):
|
||||
|
||||
# Verify prepare was called with correct arguments
|
||||
mock_pf_instance.prepare.assert_called_once_with(
|
||||
hidden_states, router_logits, False, False, False, None)
|
||||
hidden_states, router_logits, False, False, None)
|
||||
|
||||
# Test finalize method
|
||||
comm_impl.finalize(h_out, reduce_results=True)
|
||||
@@ -153,7 +153,7 @@ class TestMoECommMethod(TestBase):
|
||||
|
||||
# Verify prepare was called with correct arguments
|
||||
mock_pf_instance.prepare.assert_called_once_with(
|
||||
hidden_states, router_logits, False, False, False, None)
|
||||
hidden_states, router_logits, False, False, None)
|
||||
|
||||
@patch("vllm_ascend.ops.moe.moe_comm_method.get_current_vllm_config")
|
||||
@patch("vllm_ascend.ops.moe.moe_comm_method.get_forward_context")
|
||||
|
||||
Reference in New Issue
Block a user