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

enhance set_stop_value_multi_ends and standardize the registration of some operators (#4525)

Browse Source 
* fix custom_ops

* paddleformers>=0.3.1
This commit is contained in:
Yuanle Liu
2025-10-21 22:06:06 +08:00
committed by GitHub
parent dc7facaa7f
commit 3b58310c26
18 changed files with 68 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/gpu_ops/limit_thinking_content_length_v1.cu
View File

@@ -80,7 +80,7 @@ void LimitThinkingContentLengthV1(const paddle::Tensor &next_tokens,
batch_size);
}
PD_BUILD_OP(limit_thinking_content_length_v1)
PD_BUILD_STATIC_OP(limit_thinking_content_length_v1)
.Inputs({"next_tokens", "max_think_lens", "step_idx", "limit_think_status"})
.Attrs({"think_end_id: int64_t"})
.Outputs({"next_tokens_out"})