Step-3.5-Flash

3.2 구성 팁

• 메모리: 높은 VRAM 용량의 GPU가 필요해요. 지원 플랫폼: H200 (4×, TP=4), MI300X/MI325X/MI350X/MI355X (4×, TP=4 EP=4).
• AMD Docker 이미지: MI300X/MI325X에는 lmsysorg/sglang:v0.5.9-rocm700-mi30x, MI350X/MI355X에는 lmsysorg/sglang:v0.5.9-rocm700-mi35x를 사용하세요.
• AMD Expert Parallelism 필요: AMD GPU에서는 항상 --tp 4와 함께 --ep 4를 사용하세요. BF16과 FP8 모델 모두 expert parallelism이 필요해요. EP가 없으면 MoE 중간 차원이 GPU들에 걸쳐 분할되고(N=320), AITER CK GEMM 비호환성이 발생해요. EP=4에서는 각 GPU가 72개의 전체 전문가(N=1280)를 처리하므로 cuda graph를 켠 상태에서 올바르게 동작해요.
• AITER JIT 컴파일: AMD에서 첫 추론은 AITER 커널 JIT 컴파일 때문에 30-40초가 걸릴 수 있어요. 이후 요청은 캐시된 커널을 사용해요.

4. 모델 호출

4.1 기본 사용

기본 API 사용과 요청 예제는 다음을 참조하세요:

• SGLang Basic Usage Guide

4.2 고급 사용

4.2.1 Reasoning Parser

Step-3.5-Flash는 reasoning 모드만 지원해요. 배포 시 reasoning parser를 활성화해 thinking과 content 섹션을 분리하세요:

sglang serve \
  --model-path stepfun-ai/Step-3.5-Flash \
  --tp 4 \
  --ep 4 \
  --reasoning-parser step3p5

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()

출력 예제:

=============== 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-3.5는 툴 호출 능력을 지원해요. 툴 호출 파서를 활성화하세요:

Python 예제:

sglang 서버를 시작하세요:

sglang serve \
  --model-path stepfun-ai/Step-3.5-Flash \
  --tp 4 \
  --ep 4 \
  --reasoning-parser step3p5 \
  --tool-call-parser step3p5

from openai import OpenAI

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)

출력 예제:

--- 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.

참고:

• reasoning parser는 모델이 툴을 어떻게 사용하기로 결정하는지 보여줘요.
• 툴 호출은 함수 이름과 인자로 명확히 표시돼요.
• 그런 다음 함수를 실행하고 결과를 다시 보내 대화를 계속할 수 있어요.

5. 벤치마크

5.1 속도 벤치마크

테스트 환경:

• 하드웨어: NVIDIA H200 GPU (4x)
• 모델: Step-3.5-Flash
• Tensor Parallelism: 4
• Expert Parallelism: 4
• sglang 버전: 0.5.8

ShareGPT_Vicuna_unfiltered 데이터셋에서 SGLang의 내장 벤치마킹 도구로 성능 평가를 수행해요. 이 데이터셋은 실제 대화 데이터를 포함해 실제 사용 시나리오에서의 성능을 더 잘 반영해요.

5.1.1 표준 시나리오 벤치마크

• 모델 배포 명령:

sglang serve \
  --model-path stepfun-ai/Step-3.5-Flash \
  --tp 4 \
  --ep 4

5.1.1.1 저동시성

• 벤치마크 명령:

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

• 테스트 결과:

============ 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 중동시성

• 벤치마크 명령:

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

• 테스트 결과:

============ 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 고동시성

• 벤치마크 명령:

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

• 테스트 결과:

============ 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 정확도 벤치마크

5.2.1 GSM8K 벤치마크

• 벤치마크 명령:

python3 -m sglang.test.few_shot_gsm8k --num-questions 200

• 결과:

  • Step-3.5-Flash

    Accuracy: 0.885
    Invalid: 0.005
    Latency: 9.986 s
    Output throughput: 1972.911 token/s
    

더 알아보기 (Learn more)

• Step-3.5-Flash
• SGLang 설치 가이드