[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:
@@ -3259,8 +3259,8 @@ class NPUModelRunner(LoRAModelRunnerMixin):
|
||||
builder = attn_group.metadata_builder
|
||||
else:
|
||||
builder = attn_group.get_metadata_builder()
|
||||
if builder.cudagraph_support.value < min_ag_support.value:
|
||||
min_ag_support = builder.cudagraph_support
|
||||
if builder.aclgraph_support.value < min_ag_support.value:
|
||||
min_ag_support = builder.aclgraph_support
|
||||
min_ag_builder_name = builder.__class__.__name__
|
||||
|
||||
# This is an imitation of compilation_config.splitting_ops_contain_attention()
|
||||
|
||||
Reference in New Issue
Block a user