apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Feature] support min_p_sampling (#2872)
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* Fastdeploy support min_p

* add test_min_p

* fix

* min_p_sampling

* update

* delete vl_gpu_model_runner.py

* fix

* Align usage of min_p with vLLM

* fix

* modified unit test

* fix test_min_sampling

* pre-commit all files

* fix

* fix

* fix

* fix xpu_model_runner.py
This commit is contained in:
lizexu123
2025-07-21 14:17:59 +08:00
committed by GitHub
parent 95a214ae43
commit 67990e0572
15 changed files with 302 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/zh/offline_inference.md
+1
View File
@@ -180,6 +180,7 @@ for output in outputs:
* temperature(float): 控制生成随机性的参数，值越高结果越随机，值越低结果越确定
* top_p(float): 概率累积分布截断阈值，仅考虑累计概率达到此阈值的最可能token集合
* top_k(int): 采样概率最高的token数量，考虑概率最高的k个token进行采样
* min_p(float): token入选的最小概率阈值(相对于最高概率token的比值，设为>0可通过过滤低概率token来提升文本生成质量)
* max_tokens(int): 限制模型生成的最大token数量（包括输入和输出）
* min_tokens(int): 强制模型生成的最少token数量，避免过早结束