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

[Mamba] - refactor: Renamed mamba_attn to mamba2_attn (#22818)

Browse Source 
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
This commit is contained in:
Asaf Joseph Gardin
2025-08-15 09:38:05 +03:00
committed by GitHub
parent 5c3fbfe46b
commit 3d232dbd19
6 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
vllm/v1/attention/backends/mamba_attn.py → vllm/v1/attention/backends/mamba2_attn.py
View File

2
vllm/v1/attention/backends/mamba_selectors.py
View File

@@ -3,7 +3,7 @@
from vllm.attention.backends.abstract import AttentionBackend
from vllm.v1.attention.backends.linear_attn import LinearAttentionBackend
from vllm.v1.attention.backends.mamba1_attn import Mamba1AttentionBackend
from vllm.v1.attention.backends.mamba_attn import Mamba2AttentionBackend
from vllm.v1.attention.backends.mamba2_attn import Mamba2AttentionBackend
def get_mamba_attn_backend(mamba_type: str) -> type[AttentionBackend]: