Devstral 2 (Mistral)

from openai import OpenAI

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

resp = client.chat.completions.create(
    model="mistralai/Devstral-Small-2-24B-Instruct-2512",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a Python function that retries a request with exponential backoff."},
    ],
    temperature=0.2,
    max_tokens=512,
)

print(resp.choices[0].message.content)

  Here's a Python function that implements exponential backoff for retrying a request. This function uses the `requests` library to make HTTP requests and includes error handling for common HTTP and connection errors.

  ```python
  import time
  import requests
  from requests.exceptions import RequestException

  def retry_with_exponential_backoff(
      url,
      max_retries=3,
      initial_delay=1,
      backoff_factor=2,
      method="GET",
      **kwargs
  ):
      """
      Retry a request with exponential backoff.

      Parameters:
      - url: The URL to request.
      - max_retries: Maximum number of retry attempts (default: 3).
      - initial_delay: Initial delay in seconds (default: 1).
      - backoff_factor: Multiplier for the delay between retries (default: 2).
      - method: HTTP method to use (default: "GET").
      - **kwargs: Additional arguments to pass to the request function (e.g., headers, data, etc.).

      Returns:
      - Response object if the request succeeds.
      - Raises an exception if all retries fail.
      """
      retry_count = 0
      delay = initial_delay

      while retry_count < max_retries:
          try:
              response = requests.request(method, url, **kwargs)
              # Check if the response status code indicates success
              if response.status_code < 400:
                  return response
              else:
                  raise RequestException(f"HTTP {response.status_code}: {response.text}")

          except RequestException as e:
              if retry_count == max_retries - 1:
                  raise Exception(f"All retries failed. Last error: {e}")

              print(f"Attempt {retry_count + 1} failed. Retrying in {delay} seconds...")
              time.sleep(delay)
...

python -m sglang.launch_server \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --tp 2 \
  --tool-call-parser mistral

from openai import OpenAI

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

# Define available 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"]
            }
        }
    }
]

# Make request with streaming to see thinking process
response = client.chat.completions.create(
    model="mistralai/Devstral-2-123B-Instruct-2512",
    messages=[
        {"role": "user", "content": "What's the weather in Beijing?"}
    ],
    tools=tools,
    temperature=0.7,
    stream=True
)

# Process streaming response
thinking_started = False
has_thinking = False
tool_calls_accumulator = {}

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

        # Accumulate tool calls
        if hasattr(delta, 'tool_calls') and delta.tool_calls:
            # Close thinking section if needed
            if has_thinking and thinking_started:
                print("\n=============== Content =================\n", flush=True)
                thinking_started = False

            for tool_call in delta.tool_calls:
                index = tool_call.index
                if index not in tool_calls_accumulator:
                    tool_calls_accumulator[index] = {
                        'name': None,
                        'arguments': ''
                    }

                if tool_call.function:
                    if tool_call.function.name:
                        tool_calls_accumulator[index]['name'] = tool_call.function.name
                    if tool_call.function.arguments:
                        tool_calls_accumulator[index]['arguments'] += tool_call.function.arguments

        # Print content
        if delta.content:
            print(delta.content, end="", flush=True)

# Print accumulated tool calls
for index, tool_call in sorted(tool_calls_accumulator.items()):
    print(f"🔧 Tool Call: {tool_call['name']}")
    print(f"   Arguments: {tool_call['arguments']}")

print()

🔧 Tool Call: get_weather
   Arguments: {"location": "Beijing"}

python3 -m sglang.launch_server \
  --model-path mistralai/Devstral-2-123B-Instruct-2512 \
  --tp 8 \
  --trust-remote-code \
  --port 8888

python3 -m sglang.launch_server \
  --model-path mistralai/Devstral-2-123B-Instruct-2512 \
  --tp 8 \
  --trust-remote-code \
  --port 8888

python3 -m sglang.bench_serving \
  --backend sglang \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 10 \
  --max-concurrency 1 \
  --request-rate inf \
  --port 8888

============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 1
Successful requests:                     10
Benchmark duration (s):                  94.30
Total input tokens:                      6101
Total input text tokens:                 6101
Total input vision tokens:               0
Total generated tokens:                  4220
Total generated tokens (retokenized):    4206
Request throughput (req/s):              0.11
Input token throughput (tok/s):          64.70
Output token throughput (tok/s):         44.75
Peak output token throughput (tok/s):    82.00
Peak concurrent requests:                2
Total token throughput (tok/s):          109.44
Concurrency:                             1.00
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   9427.59
Median E2E Latency (ms):                 5637.23
---------------Time to First Token----------------
Mean TTFT (ms):                          4253.85
Median TTFT (ms):                        116.95
P99 TTFT (ms):                           37764.48
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          12.28
Median TPOT (ms):                        12.29
P99 TPOT (ms):                           12.30
---------------Inter-Token Latency----------------
Mean ITL (ms):                           12.29
Median ITL (ms):                         12.29
P95 ITL (ms):                            12.38
P99 ITL (ms):                            12.42
Max ITL (ms):                            12.90
==================================================

python -m sglang.bench_serving \
  --backend sglang \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 80 \
  --max-concurrency 16 \
  --request-rate inf \
  --port 8888

============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 16
Successful requests:                     80
Benchmark duration (s):                  52.11
Total input tokens:                      39668
Total input text tokens:                 39668
Total input vision tokens:               0
Total generated tokens:                  40805
Total generated tokens (retokenized):    40761
Request throughput (req/s):              1.54
Input token throughput (tok/s):          761.31
Output token throughput (tok/s):         783.13
Peak output token throughput (tok/s):    1120.00
Peak concurrent requests:                20
Total token throughput (tok/s):          1544.44
Concurrency:                             13.60
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   8856.19
Median E2E Latency (ms):                 9314.71
---------------Time to First Token----------------
Mean TTFT (ms):                          398.80
Median TTFT (ms):                        127.81
P99 TTFT (ms):                           1500.32
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          17.32
Median TPOT (ms):                        16.90
P99 TPOT (ms):                           32.78
---------------Inter-Token Latency----------------
Mean ITL (ms):                           16.61
Median ITL (ms):                         14.26
P95 ITL (ms):                            15.07
P99 ITL (ms):                            114.46
Max ITL (ms):                            1224.45
==================================================

python -m sglang.bench_serving \
  --backend sglang \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 500 \
  --max-concurrency 100 \
  --request-rate inf \
  --port 8888

============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 100
Successful requests:                     500
Benchmark duration (s):                  116.08
Total input tokens:                      249831
Total input text tokens:                 249831
Total input vision tokens:               0
Total generated tokens:                  252662
Total generated tokens (retokenized):    252523
Request throughput (req/s):              4.31
Input token throughput (tok/s):          2152.21
Output token throughput (tok/s):         2176.60
Peak output token throughput (tok/s):    3600.00
Peak concurrent requests:                107
Total token throughput (tok/s):          4328.81
Concurrency:                             92.42
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   21456.71
Median E2E Latency (ms):                 20126.82
---------------Time to First Token----------------
Mean TTFT (ms):                          291.60
Median TTFT (ms):                        199.24
P99 TTFT (ms):                           866.02
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          42.42
Median TPOT (ms):                        45.18
P99 TPOT (ms):                           53.32
---------------Inter-Token Latency----------------
Mean ITL (ms):                           41.97
Median ITL (ms):                         27.59
P95 ITL (ms):                            130.43
P99 ITL (ms):                            137.87
Max ITL (ms):                            616.73
==================================================

python3 benchmark/gsm8k/bench_sglang.py \
  --num-shots 8 \
  --num-questions 1316 \
  --parallel 1316 \
  --port 8888

Accuracy: 0.922
Invalid: 0.000
Latency: 35.800 s
Output throughput: 4507.697 token/s