[Refactor] Rename cudagraph_support to aclgraph_support (#3104)

### What this PR does / why we need it?
Updates the `cudagraph_support` attribute to `aclgraph_support` to use
terminology appropriate for the Ascend platform (ACL graphs instead of
CUDA graphs).

This change also explicitly disables graph support for the MLA attention
backend.

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

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

- vLLM version: v0.10.2
- vLLM main:
5aeb925452

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
This commit is contained in:
Yizhou
2025-09-23 11:30:31 +08:00
committed by GitHub
parent d2399ab97b
commit 39a85c49fa
3 changed files with 10 additions and 5 deletions

View File

@@ -199,8 +199,8 @@ class AscendMetadata:
class AscendAttentionMetadataBuilder:
# Does this backend/builder support CUDA Graphs for attention (default: no).
cudagraph_support: ClassVar[AttentionCGSupport] = \
# Does this backend/builder support ACL Graphs for attention (default: no).
aclgraph_support: ClassVar[AttentionCGSupport] = \
AttentionCGSupport.UNIFORM_SINGLE_TOKEN_DECODE
# Does this backend/builder reorder the batch?
# If not, set this to None. Otherwise set it to the query