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

[Bugfix] add qwen3 reasoning-parser fix content is None when disable … (#17369)

Browse Source 
Signed-off-by: mofanke <mofanke@gmail.com>
This commit is contained in:
mofanke
2025-04-30 00:32:40 +08:00
committed by GitHub
parent 24e6ad3f16
commit a39203f99e
4 changed files with 282 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/source/features/reasoning_outputs.md
View File

@@ -15,6 +15,7 @@ vLLM currently supports the following reasoning models:
| [DeepSeek R1 series](https://huggingface.co/collections/deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d) | `deepseek_r1` | `guided_json`, `guided_regex` | ❌ |
| [QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) | `deepseek_r1` | `guided_json`, `guided_regex` | ✅ |
| [IBM Granite 3.2 language models](https://huggingface.co/collections/ibm-granite/granite-32-language-models-67b3bc8c13508f6d064cff9a) | `granite` | ❌ | ❌ |
| [Qwen3 series](https://huggingface.co/collections/Qwen/qwen3-67dd247413f0e2e4f653967f) | `qwen3` | `guided_json`, `guided_regex` | ✅ |
- IBM Granite 3.2 reasoning is disabled by default; to enable it, you must also pass `thinking=True` in your `chat_template_kwargs`.