apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-25 09:31:38 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

[Feature] support prompt repetition_penalty (#2954)

Browse Source 
* [Feature] support prompt repetition_penalty (#2806)

* [Bug Fix] fix bug of prompt penalty (#2888)
This commit is contained in:
ming1753
2025-07-22 19:42:33 +08:00
committed by GitHub
parent 535a15ab8f
commit 69be77c8c0
8 changed files with 305 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/model_executor/layers/sample/ops/apply_penalty_multi_scores.py
View File

@@ -21,6 +21,8 @@ from fastdeploy.platforms import current_platform
def apply_penalty_multi_scores(
pre_token_ids: paddle.Tensor,
prompt_ids: paddle.Tensor,
prompt_lens: paddle.Tensor,
logits: paddle.Tensor,
repetition_penalties: paddle.Tensor,
frequency_penalties: paddle.Tensor,
@@ -39,6 +41,8 @@ def apply_penalty_multi_scores(
get_token_penalty_multi_scores
logits = get_token_penalty_multi_scores(
pre_token_ids,
prompt_ids,
prompt_lens,
logits,
repetition_penalties,
frequency_penalties,
@@ -69,6 +73,8 @@ def apply_penalty_multi_scores(
get_token_penalty_multi_scores
logits = get_token_penalty_multi_scores(
pre_token_ids,
prompt_ids,
prompt_lens,
logits,
repetition_penalties,
frequency_penalties,