xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-25 06:44:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Modify CacheConfig import (#23459)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-08-23 14:05:27 +08:00 committed by GitHub
parent b8f17f5d98
commit 65197a5fb3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/attention/layers/encoder_only_attention.py
View File

@ -5,13 +5,13 @@ from copy import copy
from typing import Optional from typing import Optional
import torch import torch
from transformers import CacheConfig
from vllm import envs from vllm import envs
from vllm.attention.backends.abstract import (AttentionBackend, from vllm.attention.backends.abstract import (AttentionBackend,
AttentionMetadata, AttentionType) AttentionMetadata, AttentionType)
from vllm.attention.layer import Attention from vllm.attention.layer import Attention
from vllm.attention.selector import get_attn_backend from vllm.attention.selector import get_attn_backend
from vllm.config import CacheConfig
from vllm.v1.attention.backends.utils import (CommonAttentionMetadata, from vllm.v1.attention.backends.utils import (CommonAttentionMetadata,
subclass_attention_backend) subclass_attention_backend)