apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 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

1
custom_ops/gpu_ops/cpp_extensions.cc
View File

@@ -77,6 +77,7 @@ std::vector<paddle::Tensor> AppendAttention(
const paddle::optional<paddle::Tensor> &cache_v_zp,
const paddle::optional<paddle::Tensor> &out_linear_shifts,
const paddle::optional<paddle::Tensor> &out_linear_smooths,
const paddle::optional<paddle::Tensor> &mask_offset,
const paddle::optional<paddle::Tensor> &kv_signal_data,
const paddle::optional<paddle::Tensor>& q_norm_weight,
const paddle::optional<paddle::Tensor>& k_norm_weight,