[Docs] Add --prerelease=allow to cookbook uv install commands (#35920)

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>

.claude/skills/cookbook-add-model/templates/page.mdx.tmpl

@@ -27,7 +27,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/Baidu/PaddleOCR-VL.mdx

@@ -19,7 +19,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/Baidu/Unlimited-OCR.mdx

@@ -22,7 +22,7 @@ uv venv --python 3.12 && source .venv/bin/activate
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
 git fetch origin pull/29186/head && git checkout FETCH_HEAD
-uv pip install -e python
+uv pip install --prerelease=allow -e python
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/DeepReinforce/Ornith-1.0.mdx

@@ -19,7 +19,7 @@ Ornith-1.0 model cards recommend SGLang `>=0.5.9`. The Deploy panel below emits
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install "sglang>=0.5.9"
+uv pip install --prerelease=allow "sglang>=0.5.9"
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx

@@ -19,7 +19,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/GLM/GLM-4.6V.mdx

@@ -41,7 +41,7 @@ git clone https://github.com/sgl-project/sglang.git
 cd sglang
 uv venv
 source .venv/bin/activate
-uv pip install -e "python[all]" --index-url=https://pypi.org/simple
+uv pip install --prerelease=allow -e "python[all]" --index-url=https://pypi.org/simple
 pip install nvidia-cudnn-cu12==9.16.0.29
 # Install ffmpeg to support video input
 sudo apt update

docs/cookbook/autoregressive/GLM/GLM-5.2.mdx

@@ -19,7 +19,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/InternLM/Intern-S1.mdx

@@ -15,7 +15,7 @@ Intern-S1 includes the large **Intern-S1** MoE model and the smaller **Intern-S1
 Refer to the [official SGLang installation guide](../../../docs/get-started/install), or install from source:
 
 ```bash Command
-uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
+uv pip install --prerelease=allow 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
 ```
 
 ## 3. Model Deployment

docs/cookbook/autoregressive/InternLM/Intern-S2-Mobius.mdx

@@ -19,7 +19,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/InternLM/Intern-S2-Preview.mdx

@@ -20,7 +20,7 @@ Install SGLang from source or use an NVIDIA Docker image:
 
 ```bash Command
 # Install from source
-uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
+uv pip install --prerelease=allow 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
 
 # Or use Docker for NVIDIA GPUs
 docker pull lmsysorg/sglang:latest

docs/cookbook/autoregressive/LiquidAI/LFM2.5.mdx

@@ -19,7 +19,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 <Note>

docs/cookbook/autoregressive/Meta/MuseGlimmer.mdx

@@ -23,7 +23,7 @@ pip install uv
 # https://github.com/sgl-project/sglang/pull/34262
 git clone -b muse-glimmer https://github.com/sgl-project/sglang.git
 cd sglang
-uv pip install -e "python[all]"
+uv pip install --prerelease=allow -e "python[all]"
 ```
 
 Run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/MiniMax/MiniMax-M3.mdx

@@ -25,10 +25,10 @@ uv venv --python 3.12 && source .venv/bin/activate
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
 git fetch origin pull/27944/head && git checkout FETCH_HEAD
-uv pip install -e python
+uv pip install --prerelease=allow -e python
 ```
 
-Then run the **Python** output of the command panel below in that environment. The **Docker** tab is simpler — its image bundles the CUDA-13 runtime and the #27944 code. Once [PR #27944](https://github.com/sgl-project/sglang/pull/27944) is merged and released, `uv pip install sglang` will pull M3 support directly.
+Then run the **Python** output of the command panel below in that environment. The **Docker** tab is simpler — its image bundles the CUDA-13 runtime and the #27944 code. Once [PR #27944](https://github.com/sgl-project/sglang/pull/27944) is merged and released, `uv pip install --prerelease=allow sglang` will pull M3 support directly.
 
 </Tab>
 

docs/cookbook/autoregressive/Moonshotai/Kimi-K3.mdx

@@ -19,7 +19,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano-Omni.mdx

@@ -46,7 +46,7 @@ Install SGLang via pip or from source:
 pip install sglang
 
 # Or install from source
-uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
+uv pip install --prerelease=allow 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
 
 # Or use Docker
 docker pull lmsysorg/sglang:latest

docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano.mdx

@@ -22,7 +22,7 @@ At a high level:
 
 Refer to the [official SGLang installation guide](../../../docs/get-started/install), or install nightly wheel through:
 ```bash Command
-uv pip install sglang==0.5.6.post3.dev1278+gad1b4e472 --extra-index-url https://sgl-project.github.io/whl/nightly/
+uv pip install --prerelease=allow sglang==0.5.6.post3.dev1278+gad1b4e472 --extra-index-url https://sgl-project.github.io/whl/nightly/
 ```
 
 ## 3. Model Deployment

docs/cookbook/autoregressive/NVIDIA/Nemotron3-Super.mdx

@@ -25,7 +25,7 @@ SGLang from the main branch is required for Nemotron3-Super. You can install fro
 
 ```bash Command
 # Install from source
-uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
+uv pip install --prerelease=allow 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
 
 # Or use Docker
 docker pull lmsysorg/sglang:latest

docs/cookbook/autoregressive/NVIDIA/Nemotron3.5-Lightning.mdx

@@ -19,7 +19,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-SGLANG_BUILD_RUST_EXTS=none uv pip install 'git+https://github.com/sgl-project/sglang.git@refs/pull/33554/head#subdirectory=python'
+SGLANG_BUILD_RUST_EXTS=none uv pip install --prerelease=allow 'git+https://github.com/sgl-project/sglang.git@refs/pull/33554/head#subdirectory=python'
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/Poolside/Laguna-M.1.mdx

@@ -23,7 +23,7 @@ uv venv --python 3.12 && source .venv/bin/activate
 # tagged release — install from main. The serving runtime is in the base dependencies, no extra needed:
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
-uv pip install -e python
+uv pip install --prerelease=allow -e python
 ```
 
 Then run the **Python** output of the command panel below in that environment. The **Docker** tab is simpler — `lmsysorg/sglang:latest` bundles the CUDA-13 runtime and the M.1 code.

docs/cookbook/autoregressive/Poolside/Laguna-S-2.1.mdx

@@ -22,7 +22,7 @@ uv venv --python 3.12 && source .venv/bin/activate
 
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
-uv pip install -e python
+uv pip install --prerelease=allow -e python
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/Poolside/Laguna-XS-2.1.mdx

@@ -23,7 +23,7 @@ uv venv --python 3.12 && source .venv/bin/activate
 
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
-uv pip install -e python
+uv pip install --prerelease=allow -e python
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx

@@ -97,7 +97,7 @@ SGLang from the main branch is required for Qwen3.5. You can install from source
 
 ```bash Command
 # Install from source
-uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
+uv pip install --prerelease=allow 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
 
 # Or use Docker (NVIDIA GPUs)
 docker pull lmsysorg/sglang:latest

docs/cookbook/autoregressive/Qwen/Qwen3.6.mdx

@@ -77,10 +77,10 @@ SGLang `>=0.5.10` is required for Qwen3.6. You can install from PyPI, from sourc
 
 ```bash Command
 # Install from PyPI
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 
 # Or install from source
-uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
+uv pip install --prerelease=allow 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
 
 # Or use Docker (NVIDIA GPUs; also serves the NVFP4 variants)
 docker pull lmsysorg/sglang:latest

docs/cookbook/autoregressive/Qwen/Qwen3.8-27B.mdx

@@ -19,14 +19,14 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 
 # For the DFLASH2 cells only — DFlash2 selector support is newer than the
 # latest release, so build from the commit those cells were validated on
 # instead of the line above:
 # git clone https://github.com/sgl-project/sglang.git && cd sglang
 # git checkout 1cf2b8c54d81802abc15dcf23a29b9cc687bc01e   # PR #35496
-# uv pip install -e "python[all]"
+# uv pip install --prerelease=allow -e "python[all]"
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/Qwen/Qwen3.8.mdx

@@ -18,7 +18,7 @@ For all methods and hardware platforms, see the [official SGLang installation gu
 ```bash Command
 pip install --upgrade pip
 pip install uv
-uv pip install sglang
+uv pip install --prerelease=allow sglang
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/RedNote/Dots3-Note.mdx

@@ -23,7 +23,7 @@ uv venv --python 3.12 && source .venv/bin/activate
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
 git fetch origin pull/33829/head && git checkout FETCH_HEAD
-uv pip install -e python
+uv pip install --prerelease=allow -e python
 ```
 
 Then run the **Python** output of the command panel below in that environment.

docs/cookbook/autoregressive/Tencent/Hy3.mdx

@@ -21,11 +21,11 @@ pip install -U uv
 uv venv --python 3.12 && source .venv/bin/activate
 
 # Install from source (main carries the suffix-aware `hunyuan` parser + the
-# HYV3 model code). Once a tagged release picks it up, `uv pip install sglang`
+# HYV3 model code). Once a tagged release picks it up,
-# is enough.
+# `uv pip install --prerelease=allow sglang` is enough.
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
-uv pip install -e python
+uv pip install --prerelease=allow -e python
 ```
 
 Run the **Python** output of the command panel below in that environment.

docs/docs/get-started/install.mdx

@@ -25,6 +25,10 @@ pip install uv
 uv pip install --prerelease=allow sglang
 ```
 
+<Note>
+Some of SGLang's dependencies only publish pre-releases on PyPI, so without `--prerelease=allow` uv older than 0.12.0 silently installs SGLang 0.5.9. On [uv 0.12.0](https://github.com/astral-sh/uv/releases/tag/0.12.0) and newer the flag is a harmless no-op.
+</Note>
+
 The major version of Cuda is 13 by default. To install sglang under Cuda 12 with pip or uv, please try the following commands:
 ```bash Command
 pip install --upgrade pip