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

[Doc] Fix DeepSeek V32 Doc (#14336)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-12-02 21:06:55 -08:00
committed by GitHub
parent d5ea8c7176
commit 4bcc5879af
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/basic_usage/deepseek_v32.md
View File

@@ -183,7 +183,7 @@ python3 -m sglang.test.run_eval --port 30000 --eval-name gpqa --num-examples 198
The mean accuracy over 8 runs shows 0.797, which matches the number 79.9 in official tech report.
```bash
Repeat: 8, mean: **0**.797
Repeat: 8, mean: 0.797
Scores: ['0.808', '0.798', '0.808', '0.798', '0.783', '0.788', '0.803', '0.793']
```
@@ -217,7 +217,7 @@ python -m sglang.launch_server --model deepseek-ai/DeepSeek-V3.2-Exp --tp 8 --dp
**For `DeepSeek-V3.2` and `DeepSeek-V3.2-Speciale`**:
Hardcode the thinking mode to be `thinking` in (`_apply_jinja_template`)[https://github.com/sgl-project/sglang/blob/7c38eca1e4a704bf09fe6b52ea040a41d3cfc55d/python/sglang/srt/entrypoints/openai/serving_chat.py#L286`], then launch the server as usual:
Hardcode the thinking mode to be `thinking` in `_apply_jinja_template` function [here](https://github.com/sgl-project/sglang/blob/7c38eca1e4a704bf09fe6b52ea040a41d3cfc55d/python/sglang/srt/entrypoints/openai/serving_chat.py#L286), then launch the server as usual:
```
python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3.2 --trust-remote-code --tp-size 8 --dp-size 8 --enable-dp-attention --tool-call-parser deepseekv32 --reasoning-parser deepseek-v3
```