A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 19:45 UTC
[Doc] Added QwQ-32B to the supported models list in the reasoning out… (#14479)
Signed-off-by: WangErXiao <863579016@qq.com>
Robin committed
Mar 8, 2025 at 15:07 UTC
c908a07f57c07562c6a208166f247e9c71bea8d1
1 file changed
+1
docs/source/features/reasoning_outputs.md
+1
@@ -13,6 +13,7 @@ vLLM currently supports the following reasoning models:
13
| Model Series | Parser Name | Structured Output Support |
14
|--------------|-------------|------------------|
15
| [DeepSeek R1 series](https://huggingface.co/collections/deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d) | `deepseek_r1` | `guided_json`, `guided_regex` |
16
+| [QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) | `deepseek_r1` | `guided_json`, `guided_regex` |
17
18
## Quickstart
19