[Attention] Refactor CUDA attention backend selection logic (#24794)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2025-11-11 07:40:44 -05:00
committed by GitHub
co-authored by Luka Govedič
parent 2e78150d24
commit b30dfa03c5
61 changed files with 1338 additions and 1002 deletions
+2 -2
View File
@@ -32,7 +32,7 @@ from pydantic.fields import FieldInfo
from typing_extensions import TypeIs, deprecated
import vllm.envs as envs
from vllm.attention.backends.registry import _Backend
from vllm.attention.backends.registry import AttentionBackendEnum
from vllm.config import (
CacheConfig,
CompilationConfig,
@@ -462,7 +462,7 @@ class EngineArgs:
MultiModalConfig.mm_shm_cache_max_object_size_mb
)
mm_encoder_tp_mode: MMEncoderTPMode = MultiModalConfig.mm_encoder_tp_mode
mm_encoder_attn_backend: _Backend | str | None = (
mm_encoder_attn_backend: AttentionBackendEnum | str | None = (
MultiModalConfig.mm_encoder_attn_backend
)
io_processor_plugin: str | None = None