biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Chore] Migrate V0 attention utils (#31891)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-07 21:44:36 +08:00
committed by GitHub
parent 974138751b
commit b665bbc2d4
10 changed files with 30 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/mamba/ops/causal_conv1d.py
View File

@@ -8,8 +8,8 @@
import numpy as np
import torch
from vllm.attention.backends.utils import PAD_SLOT_ID
from vllm.triton_utils import tl, triton
from vllm.v1.attention.backends.utils import PAD_SLOT_ID
@triton.jit()

2
vllm/model_executor/layers/mamba/ops/mamba_ssm.py
View File

@@ -8,8 +8,8 @@ import torch
from packaging import version
from vllm import _custom_ops as ops
from vllm.attention.backends.utils import PAD_SLOT_ID
from vllm.triton_utils import HAS_TRITON, tl, triton
from vllm.v1.attention.backends.utils import PAD_SLOT_ID
TRITON3 = HAS_TRITON and (version.parse(triton.__version__) >= version.parse("3.0.0"))