[4/N][Attention] Move MLA common to model_executor (#32060)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2026-01-13 09:08:45 -08:00
committed by GitHub
co-authored by Luka Govedič
parent 4f3676e726
commit 2263d44b68
14 changed files with 50 additions and 44 deletions
+3 -1
View File
@@ -183,7 +183,9 @@ class EagleProposer:
rocm_types.append(AiterFlashAttentionMetadata)
# TRITON_MLA backend support for MLA models (e.g., DeepSeek)
from vllm.v1.attention.backends.mla.common import MLACommonMetadata
from vllm.model_executor.layers.attention.mla_attention import (
MLACommonMetadata,
)
rocm_types.append(MLACommonMetadata)