apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-31 03:46:40 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Remove redundant inplace outputs for append_attention (#4341)

Browse Source
This commit is contained in:
Nyakku Shigure
2025-10-10 10:45:26 +08:00
committed by GitHub
parent 18f9c41370
commit fd5fd0bdd7
1 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
custom_ops/gpu_ops/append_attention.cu
View File

@@ -1065,9 +1065,7 @@ PD_BUILD_STATIC_OP(append_attention)
paddle::Optional("kv_signal_data"), paddle::Optional("kv_signal_data"),
paddle::Optional("q_norm_weight"), paddle::Optional("q_norm_weight"),
paddle::Optional("k_norm_weight")}) paddle::Optional("k_norm_weight")})
.Outputs({"fmha_out", "key_cache_out", "value_cache_out"}) .Outputs({"fmha_out"})
.SetInplaceMap({{"key_cache", "key_cache_out"},
{"value_cache", "value_cache_out"}})
.Attrs({"rms_norm_eps: float", .Attrs({"rms_norm_eps: float",
"compute_type: std::string", "compute_type: std::string",
"cache_quant_type: std::string", "cache_quant_type: std::string",