iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Attention] Mamba attention module refactor - Final part (#44857)

Browse Source
This commit is contained in:
wangxiyuan
2026-08-07 11:27:10 -07:00
committed by GitHub
parent 45273b8dcb
commit 4eccf906ca
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/model_executor/layers/mamba/short_conv.py
+3 -3
View File
@@ -7,7 +7,7 @@ import torch
from vllm.config import CacheConfig, ModelConfig, get_current_vllm_config
from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.forward_context import ForwardContext, get_forward_context
from vllm.model_executor.custom_op import CustomOp
from vllm.model_executor.custom_op import PluggableLayer
from vllm.model_executor.layers.linear import (
ColumnParallelLinear,
MergedColumnParallelLinear,
@@ -32,8 +32,8 @@ from vllm.v1.attention.backends.short_conv_attn import ShortConvAttentionMetadat
# --8<-- [start:short_conv]
@CustomOp.register("short_conv")
class ShortConv(MambaBase, CustomOp):
@PluggableLayer.register("short_conv")
class ShortConv(MambaBase, PluggableLayer):
# --8<-- [end:short_conv]
def __init__(