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

[1/N][Attention] Restructure attention: move files (#31916)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-09 16:10:24 -05:00
committed by GitHub
parent 1f8b7c536b
commit 2612ba9285
195 changed files with 426 additions and 396 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/mamba/mamba_mixer2.py
View File

@@ -5,7 +5,6 @@
import torch
from torch import nn
from vllm.attention.backends.abstract import AttentionMetadata
from vllm.config import CacheConfig, ModelConfig, get_current_vllm_config
from vllm.distributed import (
divide,
@@ -43,6 +42,7 @@ from vllm.model_executor.model_loader.weight_utils import (
)
from vllm.model_executor.utils import set_weight_attrs
from vllm.utils.torch_utils import direct_register_custom_op
from vllm.v1.attention.backend import AttentionMetadata
from vllm.v1.attention.backends.mamba2_attn import Mamba2AttentionMetadata
# Added by the IBM Team, 2024