docs: add MUSA initialization docs.

astro.config.mjs

@@ -93,6 +93,11 @@ export default defineConfig({
 							translations: { 'zh-CN': '沐曦 MACA' },
 							slug: 'hardware/metax_maca',
 						},
+						{
+							label: 'Mthreads MUSA',
+							translations: { 'zh-CN': '摩尔线程 MUSA' },
+							slug: 'hardware/musa',
+						},
 					],
 				},
 				{

src/content/docs/en/getting_started/launch_xllm.md

@@ -199,3 +199,45 @@ do
     --node_rank=$i \ > $LOG_FILE 2>&1 &
 done
 ```
+
+## Mthreads MUSA
+
+```bash
+#!/bin/bash
+set -e
+
+rm -rf core.*
+
+export MUSA_VISIBLE_DEVICES=0
+
+MODEL_PATH="/path/to/model/Qwen3.5-27B"
+MASTER_NODE_ADDR="127.0.0.1:9748"
+START_PORT=18000
+START_DEVICE=0
+LOG_DIR="log"
+NNODES=1
+
+mkdir -p $LOG_DIR
+
+for (( i=0; i<$NNODES; i++ ))
+do
+  PORT=$((START_PORT + i))
+  DEVICE=$((START_DEVICE + i))
+  LOG_FILE="$LOG_DIR/node_$i.log"
+  xllm \
+    --model $MODEL_PATH \
+    --devices="musa:$DEVICE" \
+    --port $PORT \
+    --master_node_addr=$MASTER_NODE_ADDR \
+    --nnodes=$NNODES \
+    --block_size=64 \
+    --max_memory_utilization=0.8 \
+    --enable_prefix_cache=false \
+    --enable_chunked_prefill=true \
+    --enable_schedule_overlap=true \
+    --enable_graph=true \
+    --node_rank=$i \ > $LOG_FILE 2>&1 &
+done
+```
+
+See [Mthreads MUSA](/en/hardware/musa/) for details.

src/content/docs/en/getting_started/quick_start.md

@@ -142,6 +142,35 @@ docker run -it \
 /bin/bash
 ```
 
+### Mthreads MUSA
+
+Image pull:
+
+```bash
+docker pull registry.mthreads.com/presale/devtech/xllm:0710
+```
+
+Container startup:
+
+```bash
+docker run -it \
+  --ipc=host \
+  --network=host \
+  --privileged \
+  --shm-size=128g \
+  --name xllm-musa \
+  --device=/dev/mtgpu0 \
+  --device=/dev/dri \
+  --group-add video \
+  --ulimit memlock=-1 \
+  -v $HOME:$HOME \
+  -w $HOME \
+  registry.mthreads.com/presale/devtech/xllm:0710 \
+  /bin/bash
+```
+
+See [Mthreads MUSA](/en/hardware/musa/) for full details.
+
 ## Build xllm
 
 If you download a release image, i.e., an image with a version number in the tag, you can skip this step because the release image comes with a pre-compiled xllm binary, and call `xllm` directly.

src/content/docs/en/hardware/musa.md

@@ -0,0 +1,84 @@
+---
+title: "Mthreads MUSA"
+description: "Run xLLM on Mthreads MUSA GPUs."
+sidebar:
+  order: 7
+---
+
+Use the MUSA device backend (`--devices=musa:<id>`) when running xLLM on Mthreads MUSA hardware.
+
+## Image and Container Startup
+
+Pull the Mthreads xLLM image:
+
+```bash
+docker pull registry.mthreads.com/presale/devtech/xllm:0710
+```
+
+Start the container:
+
+```bash
+docker run -it \
+  --ipc=host \
+  --network=host \
+  --privileged \
+  --shm-size=128g \
+  --name xllm-musa \
+  --device=/dev/mtgpu0 \
+  --device=/dev/dri \
+  --group-add video \
+  --ulimit memlock=-1 \
+  -v $HOME:$HOME \
+  -w $HOME \
+  registry.mthreads.com/presale/devtech/xllm:0710 \
+  /bin/bash
+```
+
+Add `--device=/dev/mtgpuN` for additional GPUs. Select the physical GPU with `export MUSA_VISIBLE_DEVICES=0`.
+
+## Server Startup Command
+
+```bash
+#!/bin/bash
+set -e
+
+rm -rf core.*
+
+export MUSA_VISIBLE_DEVICES=0
+
+MODEL_PATH="/path/to/model/Qwen3.5-27B"
+MASTER_NODE_ADDR="127.0.0.1:9748"
+START_PORT=18000
+START_DEVICE=0
+LOG_DIR="log"
+NNODES=1
+
+mkdir -p $LOG_DIR
+
+for (( i=0; i<$NNODES; i++ ))
+do
+  PORT=$((START_PORT + i))
+  DEVICE=$((START_DEVICE + i))
+  LOG_FILE="$LOG_DIR/node_$i.log"
+  xllm \
+    --model $MODEL_PATH \
+    --devices="musa:$DEVICE" \
+    --port $PORT \
+    --master_node_addr=$MASTER_NODE_ADDR \
+    --nnodes=$NNODES \
+    --block_size=64 \
+    --max_memory_utilization=0.8 \
+    --enable_prefix_cache=false \
+    --enable_chunked_prefill=true \
+    --enable_schedule_overlap=true \
+    --enable_graph=true \
+    --node_rank=$i \ > $LOG_FILE 2>&1 &
+done
+```
+
+For a single-device run, the logical device id usually starts at `0`. For multi-GPU or multi-node deployments, keep device ids, `--node_rank`, `--nnodes`, and service ports aligned with your topology.
+
+## Notes
+
+- Image and container startup are also listed in [Quick Start](/en/getting_started/quick_start/).
+- Launch flags and multi-node setup are covered in [Launch xllm](/en/getting_started/launch_xllm/).

src/content/docs/en/hardware/overview.md

@@ -14,6 +14,7 @@ xLLM supports multiple accelerator backends for large-scale model inference. Thi
 - [Cambricon MLU](/en/hardware/cambricon_mlu/) - MLU backend setup and launch entry points.
 - [Hygon DCU](/en/hardware/dcu/) - Hygon DCU backend setup and launch entry points.
 - [MetaX MACA](/en/hardware/metax_maca/) - MetaX MACA backend setup and launch entry points.
+- [Mthreads MUSA](/en/hardware/musa/) - Mthreads MUSA GPU image, build, and `--devices=musa` launch entry points.
 
 ## Common Workflow
 

src/content/docs/zh/getting_started/launch_xllm.md

@@ -199,3 +199,45 @@ do
     --node_rank=$i \ > $LOG_FILE 2>&1 &
 done
 ```
+
+## 摩尔线程 MUSA
+
+```bash
+#!/bin/bash
+set -e
+
+rm -rf core.*
+
+export MUSA_VISIBLE_DEVICES=0
+
+MODEL_PATH="/path/to/model/Qwen3.5-27B"
+MASTER_NODE_ADDR="127.0.0.1:9748"
+START_PORT=18000
+START_DEVICE=0
+LOG_DIR="log"
+NNODES=1
+
+mkdir -p $LOG_DIR
+
+for (( i=0; i<$NNODES; i++ ))
+do
+  PORT=$((START_PORT + i))
+  DEVICE=$((START_DEVICE + i))
+  LOG_FILE="$LOG_DIR/node_$i.log"
+  xllm \
+    --model $MODEL_PATH \
+    --devices="musa:$DEVICE" \
+    --port $PORT \
+    --master_node_addr=$MASTER_NODE_ADDR \
+    --nnodes=$NNODES \
+    --block_size=64 \
+    --max_memory_utilization=0.8 \
+    --enable_prefix_cache=false \
+    --enable_chunked_prefill=true \
+    --enable_schedule_overlap=true \
+    --enable_graph=true \
+    --node_rank=$i \ > $LOG_FILE 2>&1 &
+done
+```
+
+详见 [摩尔线程 MUSA](/zh/hardware/musa/)。

src/content/docs/zh/getting_started/quick_start.md

@@ -142,6 +142,35 @@ docker run -it \
 /bin/bash
 ```
 
+### 摩尔线程 MUSA
+
+镜像拉取命令：
+
+```bash
+docker pull registry.mthreads.com/presale/devtech/xllm:0710
+```
+
+容器启动命令：
+
+```bash
+docker run -it \
+  --ipc=host \
+  --network=host \
+  --privileged \
+  --shm-size=128g \
+  --name xllm-musa \
+  --device=/dev/mtgpu0 \
+  --device=/dev/dri \
+  --group-add video \
+  --ulimit memlock=-1 \
+  -v $HOME:$HOME \
+  -w $HOME \
+  registry.mthreads.com/presale/devtech/xllm:0710 \
+  /bin/bash
+```
+
+更多细节见 [摩尔线程 MUSA](/zh/hardware/musa/)。
+
 ## 编译xllm
 
 如果下载的是release镜像，即tag中带有版本号的镜像，可以跳过此步，因为release镜像自带编译好的xllm二进制文件，可以直接调用`xllm`。

src/content/docs/zh/hardware/musa.md

@@ -0,0 +1,84 @@
+---
+title: "摩尔线程 MUSA"
+description: "在摩尔线程 MUSA GPU 上使用 xLLM 进行大模型推理部署。"
+sidebar:
+  order: 7
+---
+
+在摩尔线程（Mthreads）MUSA GPU 上部署 xLLM 时使用 MUSA 设备后端（`--devices=musa:<id>`）。
+
+## 镜像和容器启动命令
+
+拉取摩尔线程 xLLM 镜像：
+
+```bash
+docker pull registry.mthreads.com/presale/devtech/xllm:0710
+```
+
+启动容器：
+
+```bash
+docker run -it \
+  --ipc=host \
+  --network=host \
+  --privileged \
+  --shm-size=128g \
+  --name xllm-musa \
+  --device=/dev/mtgpu0 \
+  --device=/dev/dri \
+  --group-add video \
+  --ulimit memlock=-1 \
+  -v $HOME:$HOME \
+  -w $HOME \
+  registry.mthreads.com/presale/devtech/xllm:0710 \
+  /bin/bash
+```
+
+按实际 GPU 数量增加 `--device=/dev/mtgpuN`；选择物理卡使用 `export MUSA_VISIBLE_DEVICES=0`。
+
+## 服务启动命令
+
+```bash
+#!/bin/bash
+set -e
+
+rm -rf core.*
+
+export MUSA_VISIBLE_DEVICES=0
+
+MODEL_PATH="/path/to/model/Qwen3.5-27B"
+MASTER_NODE_ADDR="127.0.0.1:9748"
+START_PORT=18000
+START_DEVICE=0
+LOG_DIR="log"
+NNODES=1
+
+mkdir -p $LOG_DIR
+
+for (( i=0; i<$NNODES; i++ ))
+do
+  PORT=$((START_PORT + i))
+  DEVICE=$((START_DEVICE + i))
+  LOG_FILE="$LOG_DIR/node_$i.log"
+  xllm \
+    --model $MODEL_PATH \
+    --devices="musa:$DEVICE" \
+    --port $PORT \
+    --master_node_addr=$MASTER_NODE_ADDR \
+    --nnodes=$NNODES \
+    --block_size=64 \
+    --max_memory_utilization=0.8 \
+    --enable_prefix_cache=false \
+    --enable_chunked_prefill=true \
+    --enable_schedule_overlap=true \
+    --enable_graph=true \
+    --node_rank=$i \ > $LOG_FILE 2>&1 &
+done
+```
+
+单卡部署时逻辑设备号通常从 `0` 开始。多卡或多机场景中，需要让设备编号、`--node_rank`、`--nnodes` 和服务端口与部署拓扑保持一致。
+
+## 注意事项
+
+- 镜像与容器启动说明亦见 [快速开始](/zh/getting_started/quick_start/)。
+- 启动参数与多机部署见 [启动 xllm](/zh/getting_started/launch_xllm/)。

src/content/docs/zh/hardware/overview.md

@@ -14,6 +14,7 @@ xLLM 支持多种加速器后端，用于大模型推理部署。本章节汇总
 - [寒武纪 MLU](/zh/hardware/cambricon_mlu/) - MLU 后端环境和启动入口。
 - [海光 DCU](/zh/hardware/dcu/) - 海光 DCU 后端环境和启动入口。
 - [沐曦 MACA](/zh/hardware/metax_maca/) - 沐曦 MACA 后端环境和启动入口。
+- [摩尔线程 MUSA](/zh/hardware/musa/) - 摩尔线程 MUSA GPU 镜像启动入口。
 
 ## 通用流程