> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sglang.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Diffusion models with AR stage like GLM-Image

> Run diffusion pipelines that delegate an AR stage to a separate SGLang server, such as GLM-Image.

## Quick Start

Run model with transformers implementation for AR stage (default)

```bash theme={null}
# Terminal 1 : launch server
sglang serve --model-path zai-org/GLM-Image --port ${PORT}
```

```bash theme={null}
# Terminal 2 : launch client
curl http://${HOST}:${PORT}/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "prompt",
    "n": 1,
    "size": "widthxheight"
  }'
```

Run model with SGLang srt implementation for AR stage (high performance)

```bash theme={null}
# Terminal 1 : launch server with AR model
sglang serve --model-path /path/to/zai-org/GLM-Image/vision_language_encoder/ \
--tokenizer-path /path/to/zai-org/GLM-Image/processor/ --enable-multimodal --port ${AR_PORT}
```

```bash theme={null}
# Terminal 2 : launch server with Diffusion model
sglang serve --model-path /path/to/zai-org/GLM-Image/ \
  --srt-encoder-url "http://${HOST}:${AR_PORT}" \
  --port ${PORT}
```

```bash theme={null}
# Terminal 3 : launch client
curl http://${HOST}:${PORT}/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "prompt",
    "n": 1,
    "size": "widthxheight"
  }'
```

## Support matrix

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <colgroup>
    <col style={{width: "10%"}} />

    <col style={{width: "45%"}} />

    <col style={{width: "45%"}} />
  </colgroup>

  <thead>
    <tr style={{borderBottom: "2px solid #d55816"}}>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Model</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Transformers backend</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>SGLang backend</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>GLM-Image</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)", whiteSpace: "nowrap"}}>T2I, I2I, V2I</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>T2I</td>
    </tr>
  </tbody>
</table>

## Deployment Assumptions & Limitations

:::warning
**Network Latency & Timeouts:** In SGLang backend mode, the Diffusion server sends an HTTP request to `--srt-encoder-url` for **every auto-regressive (AR) step**.

* To prevent requests from breaking during long model generations, increase `--srt-encoder-timeout` (e.g., set to 100 seconds).

* To protect the system against temporary network delays or brief drops in connection, use `--srt-encoder-connection-timeout`.
  :::

* **Recommended Setup:** Run both servers on the same machine or inside the same fast local network.

* **Cross-Region Warning:** Running the Diffusion server and the AR server in different geographic regions will slow down token generation and heavily reduce performance.

* **Startup Connection Check:** SGLang automatically checks the connection to `--srt-encoder-url` when starting up. The server will stop immediately if the remote AR host is offline.

## Ascend NPU ENV

To run 2 servers on same group of NPU you need to specify env variables
[https://www.hiascend.com/document/detail/zh/canncommercial/850/maintenref/envvar/envref\_07\_0144.html](https://www.hiascend.com/document/detail/zh/canncommercial/850/maintenref/envvar/envref_07_0144.html)

Example:

```bash theme={null}
# Terminal 1 : server with AR model
export HCCL_IF_BASE_PORT=23000
export HCCL_HOST_SOCKET_PORT_RANGE="23000-23199"
export HCCL_NPU_SOCKET_PORT_RANGE="23200-23399"
```

```bash theme={null}
# Terminal 2 : server with diffusion model
export HCCL_IF_BASE_PORT=24000
export HCCL_HOST_SOCKET_PORT_RANGE="24000-24199"
export HCCL_NPU_SOCKET_PORT_RANGE="24200-24399"
```

## Best practices

GLM-Image example for Ascend A3 2 cards (4 devices)

```bash theme={null}
# Terminal 1 : server with AR model
export HCCL_IF_BASE_PORT=23000
export HCCL_HOST_SOCKET_PORT_RANGE="23000-23199"
export HCCL_NPU_SOCKET_PORT_RANGE="23200-23399"
sglang serve --model-path /path/to/zai-org/GLM-Image/vision_language_encoder/ \
--tokenizer-path /path/to/zai-org/GLM-Image/processor/ --enable-multimodal \
--cuda-graph-bs 1 --device npu --attention-backend ascend --disable-fast-image-processor \
--tp-size 4 --port ${PORT} --mem-fraction-static 0.4
```

Second terminal with diffusion server:

```bash theme={null}
# Terminal 2 : run SGL-Diffusion generate command
export HCCL_IF_BASE_PORT=24000
export HCCL_HOST_SOCKET_PORT_RANGE="24000-24199"
export HCCL_NPU_SOCKET_PORT_RANGE="24200-24399"
SGLANG_CACHE_DIT_FN=2 SGLANG_CACHE_DIT_BN=1 SGLANG_CACHE_DIT_WARMUP=4 SGLANG_CACHE_DIT_RDT=0.4 \
SGLANG_CACHE_DIT_MC=4 SGLANG_CACHE_DIT_TAYLORSEER=true SGLANG_CACHE_DIT_TS_ORDER=2 \
SGLANG_CACHE_DIT_ENABLED=true sglang generate --model-path /path/to/zai-org/GLM-Image/ \
--prompt "A curious raccoon" --height 1920 --width 1088 --num-inference-steps 50 --num-gpus 4 \
--sp-degree 4 --srt-encoder-url "http://${HOST}:${PORT}" --warmup
```

Result:

```bash theme={null}
Warmed-up request processed in 33.82 seconds (with warmup excluded)
```