EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 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
docs/references/environment_variables.md
View File

@@ -74,6 +74,7 @@ SGLang supports various environment variables that can be used to configure its
| `SGLANG_BLOCK_NONZERO_RANK_CHILDREN` | Control blocking of non-zero rank children processes | `1` |
| `SGL_IS_FIRST_RANK_ON_NODE` | Indicates if the current process is the first rank on its node | `"true"` |
| `SGLANG_PP_LAYER_PARTITION` | Pipeline parallel layer partition specification | Not set |
| `SGLANG_ONE_VISIBLE_DEVICE_PER_PROCESS` | Set one visible device per process for distributed computing | `false` |
## Testing & Debugging (Internal/CI)