chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Set CUDA_VISIBLE_DEVICES to achieve one GPU per process (#9170)

Browse Source 
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: Cheng Wan <cwan@x.ai>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
This commit is contained in:
Lianmin Zheng
2025-10-17 17:30:06 -07:00
committed by GitHub
parent 69fe3c9726
commit 9eefe2c0b7
7 changed files with 69 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
python/sglang/srt/environ.py
View File

@@ -142,6 +142,7 @@ class Envs:
# Model Parallel
SGLANG_USE_MESSAGE_QUEUE_BROADCASTER = EnvBool(True)
SGLANG_ONE_VISIBLE_DEVICE_PER_PROCESS = EnvBool(False)
# Constrained Decoding
SGLANG_DISABLE_OUTLINES_DISK_CACHE = EnvBool(True)