biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Add DeepSeek-V3.1 reasoning parser (split from PR #24972) (#25589)

Browse Source 
Signed-off-by: taohui <taohui3@gmail.com>
Signed-off-by: Tao Hui <taohui3@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
This commit is contained in:
Tao Hui
2025-10-15 11:09:52 +08:00
committed by GitHub
parent a2986b3e33
commit 85a65e7f51
6 changed files with 215 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/features/reasoning_outputs.md
View File

@@ -11,6 +11,7 @@ vLLM currently supports the following reasoning models:
| Model Series | Parser Name | Structured Output Support | Tool Calling |
|--------------|-------------|------------------|-------------|
| [DeepSeek R1 series](https://huggingface.co/collections/deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d) | `deepseek_r1` | `json`, `regex` | ❌ |
| [DeepSeek-V3.1](https://huggingface.co/collections/deepseek-ai/deepseek-v31-68a491bed32bd77e7fca048f) | `deepseek_v3` | `json`, `regex` | ❌ |
| [ERNIE-4.5-VL series](https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-PT) | `ernie45` | `json`, `regex` | ❌ |
| [ERNIE-4.5-21B-A3B-Thinking](https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking) | `ernie45` | `json`, `regex` | ✅ |
| [QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) | `deepseek_r1` | `json`, `regex` | ✅ |
@@ -20,8 +21,9 @@ vLLM currently supports the following reasoning models:
| [GLM-4.5 series](https://huggingface.co/collections/zai-org/glm-45-687c621d34bda8c9e4bf503b) | `glm45` | `json`, `regex` | ✅ |
!!! note
IBM Granite 3.2 reasoning is disabled by default; to enable it, you must also pass `thinking=True` in your `chat_template_kwargs`.
IBM Granite 3.2 and DeepSeek-V3.1 reasoning is disabled by default; to enable it, you must also pass `thinking=True` in your `chat_template_kwargs`.
The reasoning feature for the Qwen3 series is enabled by default. To disable it, you must pass `enable_thinking=False` in your `chat_template_kwargs`.
DeepSeek-V3.1 tool calling is supported in non-thinking mode.
## Quickstart