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

[Refactor] Unify full-graph parameter update logic (#6041)

Browse Source 
### What this PR does / why we need it?

**Refactor: Unify full-graph parameter update logic**

This PR consolidates the scattered full-graph parameter update logic
into a unified approach, improving code architecture and eliminating
duplication.

**Key improvements:**

1. **Unified interface**
- Create `update_full_graph_params` as the single entry point for all
full-graph updates
   - Replace multiple scattered update calls with one unified function
- Remove ~50 lines of duplicated if-else logic across
`model_runner_v1.py` and `eagle_proposer.py`

2. **Better architecture**
- Move update logic to respective Backend classes
(`AscendAttentionBackend`, `AscendMLABackend`)
   - Each Backend manages its own parameter update logic internally
   - Simplify caller code to just dispatch to the appropriate Backend

3. **Cleaner parameter handling**
   - Remove unnecessary `pcp_size` and `dcp_size` parameter passing
   - Get parallel configuration directly from distributed groups
   - Consistent with how other parts of the codebase obtain these values

**Why we need it:**
- **Maintainability**: Future changes only need to be made in one place
per Backend
- **Code quality**: Follows DRY principle and Single Responsibility
Principle
- **Readability**: Cleaner, more intuitive code structure

### Does this PR introduce _any_ user-facing change?

**No.** This is a pure refactoring with no functional changes - same
behavior, cleaner code.

### How was this patch tested?

- All existing unit tests pass with updated mocks
- No new tests needed (pure refactoring, no behavior changes)
- CI validates correctness

---

- vLLM version: v0.13.0

Signed-off-by: lico67373 <918688502@qq.com>
Co-authored-by: drslark <slarksblood@qq.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
This commit is contained in:
LICO67373
2026-01-24 20:12:57 +08:00
committed by GitHub
parent 8129c429ef
commit 8966a99710
10 changed files with 420 additions and 415 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/ut/spec_decode/test_eagle_proposer.py
View File

@@ -333,11 +333,11 @@ class TestEagleProposerDummyRun(TestBase):
self.proposer.dummy_run(num_tokens=64, with_prefill=True, num_reqs=4)
self.assertTrue(self.proposer._runnable.call_count == 1)
@patch("vllm_ascend.spec_decode.eagle_proposer.update_attn_params")
@patch("vllm_ascend.spec_decode.eagle_proposer.update_full_graph_params")
@patch("vllm_ascend.spec_decode.eagle_proposer.get_forward_context")
@patch("vllm_ascend.spec_decode.eagle_proposer.set_ascend_forward_context")
def test_dummy_run_in_graph_capture(self, mock_context, mock_get_context,
mock_update_attn_params):
mock_update_full_graph_params):
last_use_cuda_graph = self.proposer.use_cuda_graph
mock_return_context = MagicMock()
mock_return_context.cudagraph_runtime_mode = CUDAGraphMode.FULL
@@ -352,14 +352,14 @@ class TestEagleProposerDummyRun(TestBase):
in_graph_capturing=True,
aclgraph_runtime_mode=CUDAGraphMode.FULL)
self.assertTrue(self.proposer._runnable.call_count == 1)
mock_update_attn_params.assert_not_called()
mock_update_full_graph_params.assert_not_called()
self.proposer.use_cuda_graph = last_use_cuda_graph
@patch("vllm_ascend.spec_decode.eagle_proposer.update_attn_params")
@patch("vllm_ascend.spec_decode.eagle_proposer.update_full_graph_params")
@patch("vllm_ascend.spec_decode.eagle_proposer.get_forward_context")
@patch("vllm_ascend.spec_decode.eagle_proposer.set_ascend_forward_context")
def test_dummy_run_in_graph_run(self, mock_context, mock_get_context,
mock_update_attn_params):
mock_update_full_graph_params):
last_use_cuda_graph = self.proposer.use_cuda_graph
mock_return_context = MagicMock()
mock_return_context.cudagraph_runtime_mode = CUDAGraphMode.FULL
@@ -374,7 +374,7 @@ class TestEagleProposerDummyRun(TestBase):
in_graph_capturing=False,
aclgraph_runtime_mode=CUDAGraphMode.FULL)
self.assertTrue(self.proposer._runnable.call_count == 1)
self.assertTrue(mock_update_attn_params.call_count == 1)
self.assertTrue(mock_update_full_graph_params.call_count == 1)
self.proposer.use_cuda_graph = last_use_cuda_graph