[Docs] minor Qwen3 and reasoning parser docs fix (#6032)

docs/backend/separate_reasoning.ipynb

@@ -8,11 +8,12 @@
     "\n",
     "SGLang supports parsing reasoning content our from \"normal\" content for reasoning models such as [DeepSeek R1](https://huggingface.co/deepseek-ai/DeepSeek-R1).\n",
     "\n",
-    "## Supported Models\n",
+    "## Supported Models & Parsers\n",
     "\n",
-    "Currently, SGLang supports the following reasoning models:\n",
-    "- [DeepSeek R1 series](https://huggingface.co/collections/deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d): The reasoning content is wrapped with `<think>` and `</think>` tags.\n",
-    "- [QwQ](https://huggingface.co/Qwen/QwQ-32B): The reasoning content is wrapped with `<think>` and `</think>` tags."
+    "| Model  |  Reasoning tags      | Parser |\n",
+    "|---------|-----------------------------|------------------|\n",
+    "| [DeepSeek‑R1 series](https://huggingface.co/collections/deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d) | `<think>` … `</think>` | `deepseek-r1`    |\n",
+    "| [Qwen3 and QwQ series](https://huggingface.co/collections/Qwen/qwen3-67dd247413f0e2e4f653967f)       | `<think>` … `</think>` | `qwen3`          |"
    ]
   },
   {
@@ -60,9 +61,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Note that `--reasoning-parser` defines the parser used to interpret responses. Currently supported parsers include:\n",
-    "\n",
-    "- deepseek-r1: DeepSeek R1 series and QwQ (e.g. deepseek-ai/DeepSeek-R1, Qwen/QwQ-32B)."
+    "Note that `--reasoning-parser` defines the parser used to interpret responses."
    ]
   },
   {

docs/supported_models/generative_models.md

@@ -16,8 +16,8 @@ python3 -m sglang.launch_server \
 
 | Model Family (Variants)             | Example HuggingFace Identifier                     | Description                                                                            |
 |-------------------------------------|--------------------------------------------------|----------------------------------------------------------------------------------------|
-| **DeepSeek** (v1, v2, v3/R1)        | `deepseek-ai/DeepSeek-R1`                        | Series of advanced reasoning-optimized models (including a 671B MoE) trained with reinforcement learning; top performance on complex reasoning, math, and code tasks. [SGLang provides Deepseek v3/R1 model-specific optimizations](https://docs.sglang.ai/references/deepseek)|
-| **Qwen** (3, 3MoE, 2.5, 2 series)       | `Qwen/Qwen3-4B-Base`, `Qwen/Qwen3-MoE-15B-A2B`       | Alibaba’s latest Qwen3 series for complex reasoning, language understanding, and generation tasks; Support for MoE variants along with previous generation 2.5, 2, etc. |
+| **DeepSeek** (v1, v2, v3/R1)        | `deepseek-ai/DeepSeek-R1`                        | Series of advanced reasoning-optimized models (including a 671B MoE) trained with reinforcement learning; top performance on complex reasoning, math, and code tasks. [SGLang provides Deepseek v3/R1 model-specific optimizations](https://docs.sglang.ai/references/deepseek) and [Reasoning Parser](https://docs.sglang.ai/backend/separate_reasoning)|
+| **Qwen** (3, 3MoE, 2.5, 2 series)       | `Qwen/Qwen3-0.6B`, `Qwen/Qwen3-30B-A3B`       | Alibaba’s latest Qwen3 series for complex reasoning, language understanding, and generation tasks; Support for MoE variants along with previous generation 2.5, 2, etc. [SGLang provides Qwen3 specific reasoning parser](https://docs.sglang.ai/backend/separate_reasoning)|
 | **Llama** (2, 3.x, 4 series)        | `meta-llama/Llama-4-Scout-17B-16E-Instruct`       | Meta’s open LLM series, spanning 7B to 400B parameters (Llama 2, 3, and new Llama 4) with well-recognized performance. [SGLang provides Llama-4 model-specific optimizations](https://docs.sglang.ai/references/llama4)  |
 | **Mistral** (Mixtral, NeMo, Small3) | `mistralai/Mistral-7B-Instruct-v0.2`             | Open 7B LLM by Mistral AI with strong performance; extended into MoE (“Mixtral”) and NeMo Megatron variants for larger scale. |
 | **Gemma** (v1, v2, v3)              | `google/gemma-3-1b-it`                            | Google’s family of efficient multilingual models (1B–27B); Gemma 3 offers a 128K context window, and its larger (4B+) variants support vision input. |