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

[Refactor][Graph] Move graph parameter logic to acl_graph module (#3101)

Browse Source 
### What this PR does / why we need it?
This is the follow-up PR of #2128 .

Moves graph parameter management components, including `GraphParams`,
`get_graph_params`, and `set_graph_params`, from the generic `utils.py`
to the more specific `compilation/acl_graph.py`.

Additionally, extracts the `update_attn_params` logic from the
`NPUModelRunner` class into a standalone function within the `acl_graph`
module.

This refactoring improves code organization by centralizing ACL
graph-related logic into its own dedicated module, enhancing modularity
and clarity.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
None needed.

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
This commit is contained in:
Yizhou
2025-09-22 22:23:14 +08:00
committed by GitHub
parent 02f89d166f
commit 3fa7cf6345
4 changed files with 84 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm_ascend/attention/attention_v1.py
View File

@@ -36,10 +36,10 @@ from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.kv_cache_interface import AttentionSpec
from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
from vllm_ascend.compilation.acl_graph import get_graph_params
from vllm_ascend.ops.attention import vanilla_chunked_prefill
from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, aligned_16,
get_graph_params, is_310p, nd_to_nz_2d,
nd_to_nz_spec)
from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, aligned_16, is_310p,
nd_to_nz_2d, nd_to_nz_spec)
def wait_for_kv_layer_from_connector(layer_name: str):