apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-13 12:23:55 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

make append_attn supports mask_offset (#3138)

Browse Source 
* make append_attn supports mask_offset

* add unittest
This commit is contained in:
lzy
2025-08-14 18:40:55 +08:00
committed by GitHub
parent 6031f9a5f5
commit 1e06b9fa6d
10 changed files with 88 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/attention/ops/append_attention.py
View File

@@ -59,6 +59,7 @@ def append_attention(
cache_v_zp: Optional[paddle.Tensor] = None,
linear_shift: Optional[paddle.Tensor] = None,
linear_smooth: Optional[paddle.Tensor] = None,
mask_offset: Optional[paddle.Tensor] = None,
kv_signal_data: Optional[paddle.Tensor] = None,
q_norm_weight: Optional[paddle.Tensor] = None,
k_norm_weight: Optional[paddle.Tensor] = None,
@@ -116,6 +117,7 @@ def append_attention(
cache_v_zp,
linear_shift,
linear_smooth,
mask_offset,
kv_signal_data,
q_norm_weight,
k_norm_weight,