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

[Optimization] compulte real max_logprobs in batch (#5430)

Browse Source
This commit is contained in:
chen
2025-12-09 14:15:05 +08:00
committed by GitHub
parent f7e832efaf
commit 76649b45c1
4 changed files with 48 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/sample/meta_data.py
View File

@@ -53,6 +53,8 @@ class SamplingMetadata:
stop_flags: Optional[paddle.Tensor] = None
prompt_ids: Optional[paddle.Tensor] = None
prompt_lens: Optional[paddle.Tensor] = None
temp_scaled_logprobs_flag: Optional[bool] = None
top_p_normalized_logprobs_flag: Optional[bool] = None
temp_scaled_logprobs: Optional[paddle.Tensor] = None
top_p_normalized_logprobs: Optional[paddle.Tensor] = None
share_inputs: Optional[Dict[str, paddle.Tensor]] = None