apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Remove redundant inplace outputs for append_attention (#4340)

Browse Source
This commit is contained in:
Nyakku Shigure
2025-10-10 10:21:27 +08:00
committed by GitHub
parent aa27b03bc0
commit 5f80862578
2 changed files with 2 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
custom_ops/gpu_ops/append_attention.cu
View File

@@ -1063,9 +1063,7 @@ PD_BUILD_STATIC_OP(append_attention)
paddle::Optional("kv_signal_data"),
paddle::Optional("q_norm_weight"),
paddle::Optional("k_norm_weight")})
.Outputs({"fmha_out", "key_cache_out", "value_cache_out"})
.SetInplaceMap({{"key_cache", "key_cache_out"},
{"value_cache", "value_cache_out"}})
.Outputs({"fmha_out"})
.Attrs({"rms_norm_eps: float",
"compute_type: std::string",
"cache_quant_type: std::string",