[6/N][Attention] Move utils to more appropriate locations (#32215)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-13 05:38:52 -08:00
committed by GitHub
parent fefce49807
commit 98f60e5acb
14 changed files with 171 additions and 181 deletions
+1 -1
View File
@@ -12,7 +12,7 @@ from vllm.config import VllmConfig
from vllm.config.compilation import CUDAGraphMode
from vllm.distributed.parallel_state import graph_capture, is_global_first_rank
from vllm.forward_context import set_forward_context
from vllm.v1.attention.backends.utils import AttentionMetadataBuilder
from vllm.v1.attention.backend import AttentionMetadataBuilder
from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.kv_cache_interface import KVCacheConfig
from vllm.v1.worker.gpu.attn_utils import build_attn_metadata
+1 -1
View File
@@ -11,7 +11,7 @@ from vllm.forward_context import set_forward_context
from vllm.logger import init_logger
from vllm.model_executor.model_loader import get_model
from vllm.triton_utils import tl, triton
from vllm.v1.attention.backends.utils import AttentionMetadataBuilder
from vllm.v1.attention.backend import AttentionMetadataBuilder
from vllm.v1.kv_cache_interface import KVCacheConfig
from vllm.v1.worker.gpu.attn_utils import build_attn_metadata
from vllm.v1.worker.gpu.block_table import BlockTables
@@ -6,7 +6,7 @@ import torch
from vllm.config import VllmConfig
from vllm.config.compilation import CUDAGraphMode
from vllm.v1.attention.backends.utils import AttentionMetadataBuilder
from vllm.v1.attention.backend import AttentionMetadataBuilder
from vllm.v1.kv_cache_interface import KVCacheConfig
from vllm.v1.worker.gpu.block_table import BlockTables
from vllm.v1.worker.gpu.cudagraph_utils import (