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

[Feature] support aclgraph for model runner v2 (#7110)

Browse Source 
### What this PR does / why we need it?
This PR aims to support aclgraph for model runner v2, please see RFC
#5208. The PR contains these modifications:
- adapt to newest commit of vllm main branch.
- supply a unified interface of extra forward context for both model
runner v1 and model runner v2.
- implement graph mode for main model. 

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

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
This commit is contained in:
Ronald
2026-03-13 09:11:46 +08:00
committed by GitHub
parent 1f71da80eb
commit c980e68d40
52 changed files with 840 additions and 309 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/ut/ops/test_moe_comm_method.py
View File

@@ -28,7 +28,7 @@ class TestMoECommMethod(TestBase):
self.moe_config.dp_group = MagicMock()
self.moe_config.global_redundant_expert_num = 0
@patch("vllm_ascend.ops.fused_moe.moe_comm_method.get_forward_context")
@patch('vllm_ascend.ascend_forward_context.get_forward_context')
@patch(
"vllm_ascend.ops.fused_moe.moe_comm_method.PrepareAndFinalizeWithAllGather"
)
@@ -73,7 +73,7 @@ class TestMoECommMethod(TestBase):
context_metadata=context_metadata)
mock_pf_instance.finalize.assert_called_once_with(h_out, True, None)
@patch("vllm_ascend.ops.fused_moe.moe_comm_method.get_forward_context")
@patch('vllm_ascend.ascend_forward_context.get_forward_context')
@patch(
"vllm_ascend.ops.fused_moe.moe_comm_method.PrepareAndFinalizeWithMC2")
@patch("vllm_ascend.ops.fused_moe.moe_comm_method.TokenDispatcherWithMC2")
@@ -116,7 +116,7 @@ class TestMoECommMethod(TestBase):
context_metadata=context_metadata)
mock_pf_instance.finalize.assert_called_once_with(h_out, True, None)
@patch("vllm_ascend.ops.fused_moe.moe_comm_method.get_forward_context")
@patch('vllm_ascend.ascend_forward_context.get_forward_context')
@patch(
"vllm_ascend.ops.fused_moe.moe_comm_method.PrepareAndFinalizeWithAll2All"
)
@@ -155,7 +155,7 @@ class TestMoECommMethod(TestBase):
mock_pf_instance.prepare.assert_called_once_with(
hidden_states, router_logits, False, False, QuantType.NONE)
@patch("vllm_ascend.ops.fused_moe.moe_comm_method.get_forward_context")
@patch('vllm_ascend.ascend_forward_context.get_forward_context')
@patch(
"vllm_ascend.ops.fused_moe.moe_comm_method.PrepareAndFinalizeWithAllGather"
)