diff --git a/custom_ops/gpu_ops/append_attention.cu b/custom_ops/gpu_ops/append_attention.cu index 765e01d40..fb325d51d 100644 --- a/custom_ops/gpu_ops/append_attention.cu +++ b/custom_ops/gpu_ops/append_attention.cu @@ -1065,9 +1065,7 @@ 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",