zdy1995love/Mistral-Medium-3.5-128B-NVFP4

vllm serve Mistral-Medium-3.5-128B-NVFP4 \
    --tokenizer-mode mistral \
    --max-model-len 98304 \
    --tool-call-parser mistral \
    --enable-auto-tool-choice \
    --max_num_batched_tokens 16384 \
    --max_num_seqs 1 \
    --gpu_memory_utilization 0.99 \
    --language-model-only \
    --kv-cache-dtype fp8_e4m3 \
    --kv-offloading-size 32 \
    --disable-hybrid-kv-cache-manager

from llmcompressor.modifiers.quantization import QuantizationModifier

recipe = QuantizationModifier(
    targets="Linear",
    scheme="NVFP4A16",
    ignore=[
        "lm_head",
        "re:.*embed_tokens$",
        "re:.*vision_tower.*",
        "re:.*multi_modal_projector.*",
    ],
)

uv pip install mistral-vibe --upgrade

display_name = "Mistral Medium 3.5 (local vLLM)"
description = "Mistral Medium 3.5 mode using local vLLM"
safety = "neutral"

active_model = "mistral-medium-3.5" # Make sure this is the only active_model entry
[[providers]]
name = "vllm"
api_base = "http://<your-host-url>:8000/v1"
api_key_env_var = ""
backend = "generic"
api_style = "reasoning"

[[models]]
name = "mistralai/Mistral-Medium-3.5-128B"
provider = "vllm"
alias = "mistral-medium-3.5"
thinking = "high"
temperature = 0.7
auto_compact_threshold = 168000

[tools.bash]
default_timeout = 1200

uv pip install -U vllm \
   --torch-backend=auto \
   --extra-index-url https://wheels.vllm.ai/nightly

python -c "import mistral_common; print(mistral_common.__version__)"
python -c "import transformers; print(transformers.__version__)"

vllm serve mistralai/Mistral-Medium-3.5-128B --tensor-parallel-size 8 \
  --tool-call-parser mistral --enable-auto-tool-choice --reasoning-parser mistral --max_num_batched_tokens 16384 --max_num_seqs 128 \
  --gpu_memory_utilization 0.8

from datetime import datetime, timedelta

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.1
# use TEMP = 0.7 for reasoning="high"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    today = datetime.today().strftime("%Y-%m-%d")
    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
    model_name = repo_id.split("/")[-1]
    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)


SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": "Write me a sentence where every word starts with the next letter in the alphabet - start with 'a' and end with 'z'.",
    },
]

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    reasoning_effort="none",
)

assistant_message = response.choices[0].message.content
print(assistant_message)

import json
from datetime import datetime, timedelta

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.1

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    today = datetime.today().strftime("%Y-%m-%d")
    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
    model_name = repo_id.split("/")[-1]
    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)


SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")

image_url = "https://math-coaching.com/img/fiche/46/expressions-mathematiques.jpg"


def my_calculator(expression: str) -> str:
    return str(eval(expression))


tools = [
    {
        "type": "function",
        "function": {
            "name": "my_calculator",
            "description": "A calculator that can evaluate a mathematical expression.",
            "parameters": {
                "type": "object",
                "properties": {
                    "expression": {
                        "type": "string",
                        "description": "The mathematical expression to evaluate.",
                    },
                },
                "required": ["expression"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "rewrite",
            "description": "Rewrite a given text for improved clarity",
            "parameters": {
                "type": "object",
                "properties": {
                    "text": {
                        "type": "string",
                        "description": "The input text to rewrite",
                    }
                },
            },
        },
    },
]

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Thanks to your calculator, compute the results for the equations that involve numbers displayed in the image.",
            },
            {
                "type": "image_url",
                "image_url": {
                    "url": image_url,
                },
            },
        ],
    },
]

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    tools=tools,
    tool_choice="auto",
    reasoning_effort="none",
)

tool_calls = response.choices[0].message.tool_calls

results = []
for tool_call in tool_calls:
    function_name = tool_call.function.name
    function_args = tool_call.function.arguments
    if function_name == "my_calculator":
        result = my_calculator(**json.loads(function_args))
        results.append(result)

messages.append({"role": "assistant", "tool_calls": tool_calls})
for tool_call, result in zip(tool_calls, results):
    messages.append(
        {
            "role": "tool",
            "tool_call_id": tool_call.id,
            "name": tool_call.function.name,
            "content": result,
        }
    )


response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    reasoning_effort="none",
)

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

from datetime import datetime, timedelta

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.7

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    today = datetime.today().strftime("%Y-%m-%d")
    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
    model_name = repo_id.split("/")[-1]
    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)


SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]


response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    reasoning_effort="high",
)

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

docker pull lmsysorg/sglang:dev-mistral-medium-3.5         # H100 / H200 (Hopper, CUDA 12.9)
docker pull lmsysorg/sglang:dev-cu13-mistral-medium-3.5    # B200 / B300 (Blackwell, CUDA 13.0)

python -m sglang.launch_server --model-path mistralai/Mistral-Medium-3.5-128B \
  --tp 8 --tool-call-parser mistral --reasoning-parser mistral

uv pip install transformers

import torch
from transformers import AutoProcessor, Mistral3ForConditionalGeneration


model_id = "mistralai/Mistral-Medium-3.5-128B"

processor = AutoProcessor.from_pretrained(model_id)
model = Mistral3ForConditionalGeneration.from_pretrained(
    model_id, device_map="auto"
)

image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]

inputs = processor.apply_chat_template(messages, return_tensors="pt", tokenize=True, return_dict=True, reasoning_effort="high")
inputs = inputs.to(model.device)

output = model.generate(
    **inputs,
    max_new_tokens=1024,
    do_sample=True,
    temperature=0.7,
)[0]

# Setting `skip_special_tokens=False` to visualize reasoning trace between [THINK] [/THINK] tags.
decoded_output = processor.decode(output[len(inputs["input_ids"][0]):], skip_special_tokens=False) 
print(decoded_output)