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

23
vllm_ascend/spec_decode/eagle_proposer.py
View File

@@ -36,10 +36,7 @@ from vllm_ascend.attention.attention_mask import AttentionMaskBuilder
from vllm_ascend.attention.attention_v1 import AscendAttentionState
from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
from vllm_ascend.compilation.acl_graph import (ACLGraphWrapper,
update_attn_dcp_pcp_params,
update_attn_params,
update_mla_attn_dcp_pcp_params,
update_mla_attn_params)
update_full_graph_params)
from vllm_ascend.ops.rotary_embedding import update_cos_sin
from vllm_ascend.ops.triton.spec_decode.utils import \
prepare_inputs_padded_kernel
@@ -1181,21 +1178,9 @@ class EagleProposer(VllmEagleProposer):
# update full-graph params for one spec token
def _update_full_graph_params(self, forward_context, num_tokens, draft_attn_metadatas=None):
if self.vllm_config.model_config.use_mla:
if self.pcp_size * self.dcp_size > 1:
update_mla_attn_dcp_pcp_params(self.update_stream,
forward_context, num_tokens)
else:
update_mla_attn_params(self.update_stream, forward_context,
num_tokens,
self.vllm_config.speculative_config)
else:
if self.pcp_size * self.dcp_size > 1:
update_attn_dcp_pcp_params(self.update_stream, forward_context,
num_tokens)
else:
update_attn_params(self.update_stream, forward_context,
num_tokens, self.vllm_config, draft_attn_metadatas)
update_full_graph_params(
self.runner.attn_backend, self.update_stream, forward_context, num_tokens,
self.vllm_config, self.vllm_config.speculative_config)
# padding tensor into desired size
def _pad_tensor(self, tensor, pad_size):