> ## 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.

# Step-3.5

export const Step35Deployment = () => {
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      items: [{
        id: 'h200',
        label: 'H200',
        default: true
      }, {
        id: 'mi300x',
        label: 'MI300X',
        default: false
      }, {
        id: 'mi325x',
        label: 'MI325X',
        default: false
      }, {
        id: 'mi350x',
        label: 'MI350X',
        default: false
      }, {
        id: 'mi355x',
        label: 'MI355X',
        default: false
      }]
    },
    modelsize: {
      name: 'modelsize',
      title: 'Model Size',
      items: [{
        id: '196b',
        label: '196B',
        subtitle: 'MOE',
        default: true
      }]
    },
    quantization: {
      name: 'quantization',
      title: 'Quantization',
      items: [{
        id: 'bf16',
        label: 'BF16',
        default: true
      }, {
        id: 'fp8',
        label: 'FP8',
        default: false
      }]
    },
    reasoningParser: {
      name: 'reasoningParser',
      title: 'Reasoning Parser',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: true
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: false
      }],
      commandRule: value => value === 'enabled' ? '--reasoning-parser step3p5' : null
    },
    toolcall: {
      name: 'toolcall',
      title: 'Tool Call Parser',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: true
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: false
      }],
      commandRule: value => value === 'enabled' ? '--tool-call-parser step3p5' : null
    },
    speculative: {
      name: 'speculative',
      title: 'Speculative Decoding',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: true
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: false
      }],
      commandRule: value => {
        if (value !== 'enabled') return null;
        let cmd = '--speculative-algorithm EAGLE \\\n  --speculative-num-steps 3 \\\n  --speculative-eagle-topk 1 \\\n  --speculative-num-draft-tokens 4 \\\n  --enable-multi-layer-eagle ';
        return cmd;
      }
    }
  };
  const modelConfigs = {
    '196b': {
      baseName: '196b',
      isMOE: true,
      h200: {
        tp: 4,
        bf16: true
      },
      mi300x: {
        tp: 4,
        bf16: true
      },
      mi325x: {
        tp: 4,
        bf16: true
      },
      mi350x: {
        tp: 4,
        bf16: true
      },
      mi355x: {
        tp: 4,
        bf16: true
      }
    }
  };
  const generateCommand = values => {
    const {hardware, modelsize: modelSize, quantization, reasoningParser} = values;
    const isAMD = hardware === 'mi300x' || hardware === 'mi325x' || hardware === 'mi350x' || hardware === 'mi355x';
    const modelSizeConfig = modelConfigs[modelSize];
    const hwConfig = modelSizeConfig[hardware];
    const quantSuffix = quantization === 'fp8' ? '-FP8' : '';
    const modelName = `stepfun-ai/Step-3.5-Flash${quantSuffix}`;
    let tpValue = hwConfig.tp;
    let cmd = '';
    cmd += 'sglang serve \\\n';
    cmd += `  --model-path ${modelName}`;
    if (tpValue > 1) {
      cmd += ` \\\n  --tp ${tpValue}`;
    }
    if (quantSuffix === '-FP8' || isAMD) {
      cmd += ` \\\n  --ep ${tpValue}`;
    }
    cmd += ' \\\n  --trust-remote-code';
    for (const [key, option] of Object.entries(options)) {
      if (option.commandRule) {
        const rule = option.commandRule(values[key], values);
        if (rule) {
          cmd += ` \\\n  ${rule}`;
        }
      }
    }
    return cmd;
  };
  const getInitialState = () => {
    const initialState = {};
    Object.entries(options).forEach(([key, option]) => {
      if (option.type === 'checkbox') {
        initialState[key] = (option.items || []).filter(item => item.default).map(item => item.id);
        return;
      }
      if (option.type === 'text') {
        initialState[key] = option.default || '';
        return;
      }
      let items = option.items || [];
      if (option.getDynamicItems) {
        const defaultValues = {};
        Object.entries(options).forEach(([innerKey, innerOption]) => {
          if (innerOption.type === 'checkbox') {
            defaultValues[innerKey] = (innerOption.items || []).filter(item => item.default).map(item => item.id);
          } else if (innerOption.type === 'text') {
            defaultValues[innerKey] = innerOption.default || '';
          } else if (innerOption.items && innerOption.items.length > 0) {
            const defaultItem = innerOption.items.find(item => item.default);
            defaultValues[innerKey] = defaultItem ? defaultItem.id : innerOption.items[0].id;
          }
        });
        items = option.getDynamicItems(defaultValues);
      }
      const defaultItem = items && items.find(item => item.default);
      initialState[key] = defaultItem ? defaultItem.id : items && items[0] ? items[0].id : '';
    });
    return initialState;
  };
  const [values, setValues] = useState(getInitialState);
  const [isDark, setIsDark] = useState(false);
  useEffect(() => {
    const checkDarkMode = () => {
      const html = document.documentElement;
      const isDarkMode = html.classList.contains('dark') || html.getAttribute('data-theme') === 'dark' || html.style.colorScheme === 'dark';
      setIsDark(isDarkMode);
    };
    checkDarkMode();
    const observer = new MutationObserver(checkDarkMode);
    observer.observe(document.documentElement, {
      attributes: true,
      attributeFilter: ['class', 'data-theme', 'style']
    });
    return () => observer.disconnect();
  }, []);
  const handleRadioChange = (optionName, value) => {
    setValues(prev => ({
      ...prev,
      [optionName]: value
    }));
  };
  const handleCheckboxChange = (optionName, itemId, isChecked) => {
    setValues(prev => {
      const currentValues = prev[optionName] || [];
      if (isChecked) {
        return {
          ...prev,
          [optionName]: [...currentValues, itemId]
        };
      }
      return {
        ...prev,
        [optionName]: currentValues.filter(id => id !== itemId)
      };
    });
  };
  const handleTextChange = (optionName, value) => {
    setValues(prev => ({
      ...prev,
      [optionName]: value
    }));
  };
  const command = generateCommand(values);
  const containerStyle = {
    maxWidth: '900px',
    margin: '0 auto',
    display: 'flex',
    flexDirection: 'column',
    gap: '4px'
  };
  const cardStyle = {
    padding: '8px 12px',
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`,
    borderLeft: `3px solid ${isDark ? '#E85D4D' : '#D45D44'}`,
    borderRadius: '4px',
    display: 'flex',
    alignItems: 'center',
    gap: '12px',
    background: isDark ? '#1f2937' : '#fff'
  };
  const titleStyle = {
    fontSize: '13px',
    fontWeight: '600',
    minWidth: '140px',
    flexShrink: 0,
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const itemsStyle = {
    display: 'flex',
    rowGap: '2px',
    columnGap: '6px',
    flexWrap: 'wrap',
    alignItems: 'center',
    flex: 1
  };
  const labelBaseStyle = {
    padding: '4px 10px',
    border: `1px solid ${isDark ? '#9ca3af' : '#d1d5db'}`,
    borderRadius: '3px',
    cursor: 'pointer',
    display: 'inline-flex',
    flexDirection: 'column',
    alignItems: 'center',
    justifyContent: 'center',
    fontWeight: '500',
    fontSize: '13px',
    transition: 'all 0.2s',
    userSelect: 'none',
    minWidth: '45px',
    textAlign: 'center',
    flex: 1,
    background: isDark ? '#374151' : '#fff',
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const checkedStyle = {
    background: '#D45D44',
    color: 'white',
    borderColor: '#D45D44'
  };
  const disabledStyle = {
    cursor: 'not-allowed',
    opacity: 0.5
  };
  const subtitleStyle = {
    display: 'block',
    fontSize: '9px',
    marginTop: '1px',
    lineHeight: '1.1',
    opacity: 0.7
  };
  const textInputStyle = {
    flex: 1,
    padding: '8px 10px',
    borderRadius: '4px',
    border: `1px solid ${isDark ? '#4b5563' : '#d1d5db'}`,
    background: isDark ? '#111827' : '#fff',
    color: isDark ? '#e5e7eb' : '#111827',
    fontSize: '13px'
  };
  const commandDisplayStyle = {
    flex: 1,
    padding: '12px 16px',
    background: isDark ? '#111827' : '#f5f5f5',
    borderRadius: '6px',
    fontFamily: "'Menlo', 'Monaco', 'Courier New', monospace",
    fontSize: '12px',
    lineHeight: '1.5',
    color: isDark ? '#e5e7eb' : '#374151',
    whiteSpace: 'pre-wrap',
    overflowX: 'auto',
    margin: 0,
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`
  };
  return <div style={containerStyle} className="not-prose">
      {Object.entries(options).map(([key, option]) => {
    if (option.condition && !option.condition(values)) {
      return null;
    }
    const items = option.getDynamicItems ? option.getDynamicItems(values) : option.items || [];
    return <div key={key} style={cardStyle}>
            <div style={titleStyle}>{option.title}</div>
            <div style={itemsStyle}>
              {option.type === 'text' ? <input type="text" value={values[option.name] || ''} placeholder={option.placeholder || ''} onChange={event => handleTextChange(option.name, event.target.value)} style={textInputStyle} /> : option.type === 'checkbox' ? (option.items || []).map(item => {
      const isChecked = (values[option.name] || []).includes(item.id);
      const isDisabled = item.required || typeof item.disabledWhen === 'function' && item.disabledWhen(values);
      return <label key={item.id} title={item.disabledReason || ''} style={{
        ...labelBaseStyle,
        ...isChecked ? checkedStyle : {},
        ...isDisabled ? disabledStyle : {}
      }}>
                      <input type="checkbox" checked={isChecked} disabled={isDisabled} onChange={event => handleCheckboxChange(option.name, item.id, event.target.checked)} style={{
        display: 'none'
      }} />
                      {item.label}
                      {item.subtitle && <small style={{
        ...subtitleStyle,
        color: isChecked ? 'rgba(255,255,255,0.85)' : 'inherit'
      }}>
                          {item.subtitle}
                        </small>}
                    </label>;
    }) : items.map(item => {
      const isChecked = values[option.name] === item.id;
      const isDisabled = Boolean(item.disabled);
      return <label key={item.id} title={item.disabledReason || ''} style={{
        ...labelBaseStyle,
        ...isChecked ? checkedStyle : {},
        ...isDisabled ? disabledStyle : {}
      }}>
                      <input type="radio" name={option.name} value={item.id} checked={isChecked} disabled={isDisabled} onChange={() => !isDisabled && handleRadioChange(option.name, item.id)} style={{
        display: 'none'
      }} />
                      {item.label}
                      {item.subtitle && <small style={{
        ...subtitleStyle,
        color: isChecked ? 'rgba(255,255,255,0.85)' : 'inherit'
      }}>
                          {item.subtitle}
                        </small>}
                    </label>;
    })}
            </div>
          </div>;
  })}
      <div style={cardStyle}>
        <div style={titleStyle}>Run this Command:</div>
        <pre style={commandDisplayStyle}>{command}</pre>
      </div>
    </div>;
};

## 1. Model Introduction

[Step-3.5-Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash) is StepFun's production-grade reasoning engine built to decouple elite intelligence from heavy compute, and cuts attention cost for low-latency, cost-effective long-context inference—purpose-built for autonomous agents in real-world workflows. The model is available in multiple quantization formats optimized for different hardware platforms.

This generation delivers comprehensive upgrades across the board:

* **Hybrid Attention Architecture**:  Interleaves Sliding Window Attention (SWA) and Global Attention (GA) with a 3:1 ratio and an aggressive 128-token window. This hybrid approach ensures consistent performance across massive datasets or long codebases while significantly reducing the computational overhead typical of standard long-context models.
* **Sparse Mixture-of-Experts**: Only 11B active parameters out of 196B parameters.
* **Multi-Layer Multi-Token Prediction (MTP)**: Equipped with a  3-way Multi-Token Prediction (MTP-3). This allows for complex, multi-step reasoning chains with immediate responsiveness.

## 2.SGLang Installation

Step-3.5-Flash is currently available in SGLang via Docker image install.

### Docker (NVIDIA)

```bash Command theme={null}
# Pull the docker image
docker pull lmsysorg/sglang:dev-pr-18084

# Launch the container
docker run -it --gpus all \
  --shm-size=32g \
  --ipc=host \
  --network=host \
  lmsysorg/sglang:dev-pr-18084 bash
```

### Docker (AMD ROCm)

```bash Command theme={null}
# For MI300X/MI325X
docker pull lmsysorg/sglang:v0.5.9-rocm700-mi30x

# For MI350X/MI355X
docker pull lmsysorg/sglang:v0.5.9-rocm700-mi35x

docker run -it \
  --device=/dev/kfd --device=/dev/dri \
  --shm-size=32g \
  --ipc=host \
  --network=host \
  --group-add video --cap-add=SYS_PTRACE \
  --security-opt seccomp=unconfined \
  lmsysorg/sglang:v0.5.9-rocm700-mi30x bash  # or mi35x for MI350X/MI355X
```

## 3.Model Deployment

This section provides deployment configurations optimized for different hardware platforms and use cases.

### 3.1 Basic Configuration

The Step-3.5-Flash series comes in only one sizes. Recommended starting configurations vary depending on hardware.

**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform, model size, quantization method, and thinking capabilities.

<Step35Deployment />

### 3.2 Configuration Tips

* **Memory**: Requires GPUs with high VRAM capacity. Supported platforms: H200 (4×, TP=4), MI300X/MI325X/MI350X/MI355X (4×, TP=4 EP=4).
* **AMD Docker Image**: Use `lmsysorg/sglang:v0.5.9-rocm700-mi30x` for MI300X/MI325X and `lmsysorg/sglang:v0.5.9-rocm700-mi35x` for MI350X/MI355X.
* **AMD Expert Parallelism Required**: On AMD GPUs, always use `--ep 4` with `--tp 4`. Both BF16 and FP8 models require expert parallelism. Without EP, the MoE intermediate dimension is split across GPUs (N=320), which triggers an AITER CK GEMM incompatibility. With EP=4, each GPU handles 72 full experts (N=1280), which works correctly with cuda graph enabled.
* **AITER JIT Compilation**: First inference on AMD may take 30-40 seconds for AITER kernel JIT compilation. Subsequent requests use cached kernels.

## 4.Model Invocation

### 4.1 Basic Usage

For basic API usage and request examples, please refer to:

* [SGLang Basic Usage Guide](../../../docs/basic_usage/send_request)

### 4.2 Advanced Usage

#### 4.2.1 Reasoning Parser

Step-3.5-Flash only supports reasoning mode. Enable the reasoning parser during deployment to separate the thinking and content sections:

```shell Command theme={null}
sglang serve \
  --model-path stepfun-ai/Step-3.5-Flash \
  --tp 4 \
  --ep 4 \
  --reasoning-parser step3p5
```

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY"
)

# Enable streaming to see the thinking process in real-time
response = client.chat.completions.create(
    model="stepfun-ai/Step-3.5-Flash",
    messages=[
        {"role": "user", "content": "Solve this problem step by step: What is 15% of 240?"}
    ],
    temperature=0.7,
    max_tokens=2048,
    stream=True
)

# Process the stream
has_thinking = False
has_answer = False
thinking_started = False

for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta

        # Print thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
            if not thinking_started:
                print("=============== Thinking =================", flush=True)
                thinking_started = True
            has_thinking = True
            print(delta.reasoning_content, end="", flush=True)

        # Print answer content
        if delta.content:
            # Close thinking section and add content header
            if has_thinking and not has_answer:
                print("\n=============== Content =================", flush=True)
                has_answer = True
            print(delta.content, end="", flush=True)

print()
```

**Output Example:**

```text Output theme={null}
=============== Thinking =================
We are asked: "What is 15% of 240?" We need to solve step by step.

Step 1: Understand that "15% of 240" means we need to calculate 15 percent of 240. In mathematical terms, it is (15/100) * 240.

Step 2: Simplify the calculation. We can compute 15% of 240 by first finding 10% of 240 and then 5% of 240, and adding them. Alternatively, we can multiply directly.

Method 1:
10% of 240 = 240 * 0.10 = 24.
5% is half of 10%, so 5% of 240 = 24 / 2 = 12.
Then 15% = 10% + 5% = 24 + 12 = 36.

Method 2: Direct multiplication: 15% = 15/100 = 0.15, so 0.15 * 240 = 36.

We can also compute fractionally: (15/100)*240 = (15*240)/100. 15*240 = 3600, divided by 100 gives 36.

Thus, the answer is 36.

We'll present the solution step by step.

=============== Content =================

To find 15% of 240, follow these steps:

1. **Convert the percentage to a decimal**:
   \( 15\% = \frac{15}{100} = 0.15 \)

2. **Multiply by the number**:
   \( 0.15 \times 240 = 36 \)

Alternatively, break it down:
- \( 10\% \text{ of } 240 = 240 \times 0.10 = 24 \)
- \( 5\% \text{ of } 240 = \frac{24}{2} = 12 \) (since 5% is half of 10%)
- \( 15\% = 10\% + 5\% = 24 + 12 = 36 \)

**Answer:** 36
```

#### 4.2.2 Tool Calling

Step-3.5 supports tool calling capabilities. Enable the tool call parser:

**Python Example:**

Start sglang server:

```shell Command theme={null}
sglang serve \
  --model-path stepfun-ai/Step-3.5-Flash \
  --tp 4 \
  --ep 4 \
  --reasoning-parser step3p5 \
  --tool-call-parser step3p5
```

```python Example theme={null}
from openai import OpenAI
import json

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY"
)

# 1. define tools
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "The city name"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "Temperature unit"}
                },
                "required": ["location"]
            }
        }
    }
]

# 2. tool run
def get_weather(location, unit="celsius"):
    return f"The weather in {location} is 22°{unit[0].upper()} and sunny."

# 3. send first request
print("--- Sending first request ---")
response = client.chat.completions.create(
    model="stepfun-ai/Step-3.5-Flash",
    messages=[
        {"role": "user", "content": "What's the weather in Beijing?"}
    ],
    tools=tools,
    temperature=1.0,
    stream=False
)

message = response.choices[0].message

# 4. Handle Reasoning Content
reasoning = getattr(message, 'reasoning_content', None)
if reasoning:
    print("=============== Thinking =================")
    print(reasoning)
    print("==========================================")

# 5. Handle Tool Calls
if message.tool_calls:
    print("\n🔧 Tool Calls detected:")
    history_messages = [
        {"role": "user", "content": "What's the weather in Beijing?"},
        message
    ]

    for tool_call in message.tool_calls:
        print(f"   Tool: {tool_call.function.name}")
        print(f"   Args: {tool_call.function.arguments}")

        args = json.loads(tool_call.function.arguments)
        tool_result = get_weather(args.get("location"), args.get("unit", "celsius"))

        history_messages.append({
            "role": "tool",
            "tool_call_id": tool_call.id,
            "content": tool_result
        })

    print("\n--- Sending tool results ---")
    final_response = client.chat.completions.create(
        model="stepfun-ai/Step-3.5-Flash",
        messages=history_messages,
        temperature=1.0,
        stream=False
    )

    print("=============== Final Content =================")
    print(final_response.choices[0].message.content)

else:
    if message.content:
        print("=============== Content =================")
        print(message.content)
```

**Output Example:**

```text Output theme={null}
--- Sending first request ---
=============== Thinking =================
The user is asking for the weather in Beijing. I should use the get_weather function with location="Beijing". The unit parameter is optional and the user didn't specify a preference, so I'll leave it out (the default should be fine).

==========================================

🔧 Tool Calls detected:
   Tool: get_weather
   Args: {"location": "Beijing"}

--- Sending tool results ---
=============== Final Content =================
The weather in Beijing is 22°C and sunny.
```

**Note:**

* The reasoning parser shows how the model decides to use a tool
* Tool calls are clearly marked with the function name and arguments
* You can then execute the function and send the result back to continue the conversation

## 5. Benchmark

### 5.1 Speed Benchmark

**Test Environment:**

* Hardware: NVIDIA H200 GPU (4x)
* Model: Step-3.5-Flash
* Tensor Parallelism: 4
* Expert Parallelism: 4
* sglang version: 0.5.8

We use SGLang's built-in benchmarking tool to conduct performance evaluation on the [ShareGPT\_Vicuna\_unfiltered](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) dataset. This dataset contains real conversation data and can better reflect performance in actual use scenarios.

#### 5.1.1 Standard Scenario Benchmark

* Model Deployment Command:

```shell Command theme={null}
sglang serve \
  --model-path stepfun-ai/Step-3.5-Flash \
  --tp 4 \
  --ep 4
```

##### 5.1.1.1 Low Concurrency

* Benchmark Command:

```shell Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --model stepfun-ai/Step-3.5-Flash \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 10 \
  --max-concurrency 1
```

* Test Results:

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 1
Successful requests:                     10
Benchmark duration (s):                  35.30
Total input tokens:                      6091
Total input text tokens:                 6091
Total generated tokens:                  4220
Total generated tokens (retokenized):    4212
Request throughput (req/s):              0.28
Input token throughput (tok/s):          172.57
Output token throughput (tok/s):         119.56
Peak output token throughput (tok/s):    124.00
Peak concurrent requests:                2
Total token throughput (tok/s):          292.14
Concurrency:                             1.00
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   3527.94
Median E2E Latency (ms):                 2884.72
P90 E2E Latency (ms):                    6350.38
P99 E2E Latency (ms):                    7858.53
---------------Time to First Token----------------
Mean TTFT (ms):                          107.53
Median TTFT (ms):                        80.93
P99 TTFT (ms):                           269.52
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          8.12
Median TPOT (ms):                        8.13
P99 TPOT (ms):                           8.14
---------------Inter-Token Latency----------------
Mean ITL (ms):                           8.12
Median ITL (ms):                         8.11
P95 ITL (ms):                            8.61
P99 ITL (ms):                            8.91
Max ITL (ms):                            20.77
==================================================
```

##### 5.1.1.2 Medium Concurrency

* Benchmark Command:

```shell Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --model stepfun-ai/Step-3.5-Flash \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 80 \
  --max-concurrency 16
```

* Test Results:

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 16
Successful requests:                     80
Benchmark duration (s):                  54.06
Total input tokens:                      39588
Total input text tokens:                 39588
Total generated tokens:                  40805
Total generated tokens (retokenized):    40479
Request throughput (req/s):              1.48
Input token throughput (tok/s):          732.33
Output token throughput (tok/s):         754.84
Peak output token throughput (tok/s):    928.00
Peak concurrent requests:                21
Total token throughput (tok/s):          1487.17
Concurrency:                             14.06
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   9501.23
Median E2E Latency (ms):                 10010.71
P90 E2E Latency (ms):                    15655.09
P99 E2E Latency (ms):                    18803.63
---------------Time to First Token----------------
Mean TTFT (ms):                          198.34
Median TTFT (ms):                        89.50
P99 TTFT (ms):                           984.66
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          18.97
Median TPOT (ms):                        18.80
P99 TPOT (ms):                           35.67
---------------Inter-Token Latency----------------
Mean ITL (ms):                           18.27
Median ITL (ms):                         17.48
P95 ITL (ms):                            18.44
P99 ITL (ms):                            62.47
Max ITL (ms):                            460.85
==================================================
```

##### 5.1.1.3 High Concurrency

* Benchmark Command:

```shell Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --model stepfun-ai/Step-3.5-Flash \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 500 \
  --max-concurrency 100
```

* Test Results:

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 100
Successful requests:                     500
Benchmark duration (s):                  125.88
Total input tokens:                      249331
Total input text tokens:                 249331
Total generated tokens:                  252662
Total generated tokens (retokenized):    251323
Request throughput (req/s):              3.97
Input token throughput (tok/s):          1980.77
Output token throughput (tok/s):         2007.23
Peak output token throughput (tok/s):    2500.00
Peak concurrent requests:                109
Total token throughput (tok/s):          3987.99
Concurrency:                             92.25
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   23223.31
Median E2E Latency (ms):                 22631.90
P90 E2E Latency (ms):                    42269.38
P99 E2E Latency (ms):                    47637.53
---------------Time to First Token----------------
Mean TTFT (ms):                          372.13
Median TTFT (ms):                        127.26
P99 TTFT (ms):                           1880.42
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          46.06
Median TPOT (ms):                        47.61
P99 TPOT (ms):                           51.34
---------------Inter-Token Latency----------------
Mean ITL (ms):                           45.31
Median ITL (ms):                         39.86
P95 ITL (ms):                            72.49
P99 ITL (ms):                            117.05
Max ITL (ms):                            1359.81
==================================================
```

### 5.2 Accuracy Benchmark

#### 5.2.1 GSM8K Benchmark

* **Benchmark Command:**

```shell Command theme={null}
python3 -m sglang.test.few_shot_gsm8k --num-questions 200
```

* **Results**:

  * Step-3.5-Flash
    ```
    Accuracy: 0.885
    Invalid: 0.005
    Latency: 9.986 s
    Output throughput: 1972.911 token/s
    ```