[Chore] Separate out vllm.utils.mem_utils (#27143)
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com> Signed-off-by: iAmir97 <71513472+iAmir97@users.noreply.github.com> Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
iAmir97
gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent
83004020fd
commit
1d165d6d85
@@ -74,8 +74,6 @@ from vllm.sequence import IntermediateTensors
|
||||
from vllm.tasks import GenerationTask, PoolingTask, SupportedTask
|
||||
from vllm.utils import (
|
||||
STR_DTYPE_TO_TORCH_DTYPE,
|
||||
DeviceMemoryProfiler,
|
||||
GiB_bytes,
|
||||
cdiv,
|
||||
check_use_alibi,
|
||||
get_dtype_size,
|
||||
@@ -85,6 +83,8 @@ from vllm.utils import (
|
||||
supports_dynamo,
|
||||
)
|
||||
from vllm.utils.jsontree import json_map_leaves
|
||||
from vllm.utils.mem_constants import GiB_bytes
|
||||
from vllm.utils.mem_utils import DeviceMemoryProfiler
|
||||
from vllm.v1.attention.backends.flash_attn import AttentionMetadata
|
||||
from vllm.v1.attention.backends.gdn_attn import GDNAttentionMetadataBuilder
|
||||
from vllm.v1.attention.backends.utils import (
|
||||
|
||||
Reference in New Issue
Block a user