apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[FIX 2.0.2] Topk topp sampling fix (#2805)

Browse Source 
* fix topk-topp

* fix
This commit is contained in:
Sunny-bot1
2025-07-10 21:15:03 +08:00
committed by GitHub
parent e681e1e719
commit 4025ea7e5b
6 changed files with 27 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/envs.py
View File

@@ -74,7 +74,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
"FD_ATTENTION_BACKEND":
lambda: os.getenv("FD_ATTENTION_BACKEND", "APPEND_ATTN"),
# Set sampling class. "base", "air" and "rejection" can be set currently.
# Set sampling class. "base", "base_non_truncated", "air" and "rejection" can be set currently.
"FD_SAMPLING_CLASS":
lambda: os.getenv("FD_SAMPLING_CLASS", "base"),