[MUSA] Add installation guide and Dockerfile (#36709)

Co-authored-by: zhiguo.qin <zhiguo.qin@mthreads.com>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>

docs/docs/hardware-platforms/mthreads_gpu.mdx

@@ -4,7 +4,20 @@ metatags:
     description: "Run SGLang on Moore Threads GPUs."
 ---
 
-This document describes how run SGLang on Moore Threads GPUs. If you encounter issues or have questions, please [open an issue](https://github.com/sgl-project/sglang/issues).
+This document describes how to run SGLang on Moore Threads GPUs. If you
+encounter issues or have questions, please [open an issue](https://github.com/sgl-project/sglang/issues).
+
+SGLang uses the MUSA runtime through
+[`torch_musa`](https://github.com/MooreThreads/torch_musa) and
+[`torchada`](https://github.com/MooreThreads/torchada). The
+`python[all_musa]` extra installs the MUSA torch, Triton, TileLang, MATE, and
+runtime Python stack from the Moore Threads package index, with public PyPI as
+the fallback for common Python dependencies.
+
+## Prerequisites
+
+Install the Moore Threads driver and MUSA toolkit before installing SGLang. For
+MTT S5000, follow the [official driver installation guide](https://docs.mthreads.com/driver-linux-server/driver-linux-server-doc-online/MTT_S5000/install_guide).
 
 ## Install SGLang
 
@@ -12,18 +25,92 @@ You can install SGLang using one of the methods below.
 
 ### Install from Source
 
-```bash
-# Use the default branch
+Start from an environment with the prerequisites above installed.
+
+```bash Command
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
 
-# Compile sgl-kernel
-pip install --upgrade pip
-cd python/sglang/kernels/aot
-python setup_musa.py install
+python -m pip install --upgrade pip "setuptools<82" wheel
+cp python/pyproject_other.toml python/pyproject.toml
+python -m pip install -e "python[all_musa]" \
+  --index-url https://dl.mthreads.com/repo/api/pypi/pypi/simple \
+  --extra-index-url https://pypi.org/simple \
+  --trusted-host dl.mthreads.com \
+  --no-build-isolation
 
-# Install sglang python package along with diffusion support
-cd ../../../..
-rm -f python/pyproject.toml && mv python/pyproject_other.toml python/pyproject.toml
-pip install -e "python[all_musa]"
+# Ensure the MUSA Triton wheel (with triton.backends.mtgpu) is installed.
+python -m pip install --no-cache-dir --force-reinstall --no-deps \
+  --index-url https://dl.mthreads.com/repo/api/pypi/pypi/simple \
+  --trusted-host dl.mthreads.com \
+  triton==3.2.0
+python -c 'import triton.backends.mtgpu'
+
+cd python/sglang/kernels/aot
+cp pyproject_musa.toml pyproject.toml
+MTGPU_TARGET=mp_31 python setup_musa.py install
+```
+
+### Install Using Docker
+
+The Dockerfile installs the MUSA runtime and Python stack declared by
+`python/pyproject_other.toml`.
+
+```bash Command
+git clone https://github.com/sgl-project/sglang.git
+cd sglang
+
+docker build -f docker/musa.Dockerfile -t sglang:main-musa .
+```
+
+Run the image with MUSA devices exposed by the host container toolkit.
+
+```bash Command
+alias drun='docker run -it --rm --network=host \
+  --env MTHREADS_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+  --env MTHREADS_DRIVER_CAPABILITIES=all \
+  --shm-size=32g \
+  -v ~/.cache/huggingface:/root/.cache/huggingface'
+
+drun sglang:main-musa \
+  python3 -c 'import triton.backends.mtgpu; print("MUSA Triton backend OK")'
+```
+
+Launch the server:
+
+```bash Command
+drun sglang:main-musa \
+  python3 -m sglang.launch_server \
+  --model-path Qwen/Qwen3-8B \
+  --host 0.0.0.0 \
+  --port 30000
+```
+
+When the server displays `The server is fired up and ready to roll!`, startup is
+successful.
+
+## Verify
+
+You can send an OpenAI-compatible request to the engine:
+
+```bash Command
+curl http://127.0.0.1:30000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "Qwen/Qwen3-8B",
+    "messages": [{"role": "user", "content": "Hello!"}],
+    "max_tokens": 32
+  }'
+```
+
+Or run a benchmark:
+
+```bash Command
+drun sglang:main-musa \
+  python3 -m sglang.bench_serving \
+  --backend sglang \
+  --dataset-name random \
+  --num-prompts 4000 \
+  --random-input 128 \
+  --random-output 128
 ```

docs/docs/hardware-platforms/overview.mdx

@@ -10,3 +10,4 @@ description: Platform-specific guides for running SGLang on GPUs, TPUs, NPUs, CP
 - [NVIDIA Jetson Orin](./nvidia_jetson)
 - [TPU](./tpu)
 - [XPU](./xpu)
+- [Moore Threads GPUs](./mthreads_gpu)

docs/index.mdx

@@ -50,7 +50,7 @@ import { PopularModels } from "/src/snippets/_popular_models.jsx";
 
 <Card title="Extensive Hardware Support" icon="microchip">
   Native support across <a href="./docs/hardware-platforms/overview">Hardware Platforms</a>
-  including NVIDIA, AMD, Intel Xeon, Google TPU, and Ascend NPU accelerators.
+  including NVIDIA, AMD, Intel Xeon, Google TPU, Ascend NPU, and Moore Threads MUSA accelerators.
 </Card>
 
   <Card title="Community & Training" icon="users">