python -m venv vllm_env
source vllm_env/bin/activate  # For Linux/macOS
# or
vllm_env\Scripts\activate     # For Windows

# Start Ray with the dashboard enabled
ray start --head --dashboard-port=8265 --include-dashboard=True 

# Run vLLM API server
CUDA_VISIBLE_DEVICES=0 python -m vllm.entrypoints.openai.api_server \
  --model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B \
  --port 9000 \
  --tensor-parallel-size 1

# For CPU (if you don’t have a GPU):
python -m vllm.entrypoints.openai.api_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --device cpu --port 9000

from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"

import requests

url = "http://localhost:9000/v1/completions"
headers = {"Content-Type": "application/json"}
data = {
    "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
    "prompt": "Write a python code that recives and int and outputs the sum of 0 to int. I do not need to see your line of thinking! Just show me the output!",
    "max_tokens": 2000
}

response = requests.post(url, headers=headers, json=data)
print(response.json()['choices'][0]['text'])

 For example, if the integer is 3, the Output... How? Ok, the integer is 3, Output is 6. Perform loop. Yes, I need to implement this in Python.

So, I know if I write a for loop from 0 to int, then sum all the numbers.

But for the for loop, how to make the range go through 0,1,2,3.

So, for that range, which parameters.

Wait, in Python, range(start, stop), and elif start is included, stop is excluded.

So, if someone wanted to sum 0 to 3 in Python.

We should perhaps set the range as range(0,4), but wait, if we do 0,1,2,3.

Wait, but the for loop will automatically go through each number. So the for [var] from 0 to int+1.

So, perhaps for i in range(0, int + 1):

So, in your code, the output is the sum of 0 to integer.

So, the meaning is: calculate 0 +1 +2 +3+...+n.

So, in Python, for integers from 0 to n, sum include all.

Thus, in this case, the example provided was, if the integer is 3, sum is 0+1+2+3=6.

Yes.

So, in code, as follows.

Problem is when the int is passed as input.

So, in Python, we have to read the integer from standard input.

Then, compute the sum.

So, first, read the integer.

One approach is to read a string from input, convert to integer. Then, loop from 0 to that integer, sum.

Wait, but according to the question, after receiving the int, output the sum.

So, that's steps.

Read integer 'n' from input.

sum = 0

for i in range(n+1):

    sum += i

print sum.

Yes.

In the example, when n is 3, sum is 6.

Yes.

Therefore, the code.

Wait, the user provides for Python.

So, in pseudocode.

n = int(input())

total = 0

for i in range(n + 1):

    total += i

print(total)

So, that's the code.

Wait, but in Python, when you do for i in ... it's inclusive.

Wait, no, because the range goes up to stop as exclusive.

Hence, for the range(n+1) needs to generate 0,1,2,...,n.

Because, for example, range(3) would give 0,1,2: that's because starting from 0, then 0 to stop -1. So, to get 0 to 3 included, the range should be 0 to 4.

Because:

range(0,4) is [0,1,2,3].

Yes.

So that's the correct approach.

So then, the code is:

n = int(input())

total = 0

for i in range(n + 1):

    total += i

print(total)

So, that should work.

Testing by input(3) gives 6.

Testing input(0) gives 0.

Testing input(1) gives 0 +1= 1. Wait, no, 0 +1 is 1? Or is the sum including 0 and 1.

Yes, sum from 0 to 1 is 0+1=1.

Wait, so, for int=1, the code will calculate (0+1)=1, which is correct.

So in this code, the sum is correct.

Thus, that's the solution.

So, putting it all together.

The code will read an integer, sum from 0 to n, then print the sum.

Yes.

Hence, the Python code is written as:

n = int(input())
total = 0
for i in range(n + 1):
    total += i
print(total)
</think>

To solve this problem, we need to write a Python code that reads an integer from the standard input, calculates the sum of all integers from 0 up to and including that integer, and prints the result.

### Approach
The approach is straightforward and involves the following steps:
1. Read an integer input from the user.
2. Initialize a variable to keep track of the sum.
3. Use a loop to iterate from 0 to the given integer, inclusive, and add each number to the sum.
4. Print the computed sum.

This solution efficiently computes the sum using a for loop within the range defined from 0 to the given integer, ensuring we include all required values.

### Solution Code
```python
n = int(input())
total = 0
for i in range(n + 1):
    total += i
print(total)
```

### Explanation
1. **Reading Input**: The input is read using `input()` and converted to an integer using `int()`.
2. **Initializing Sum**: A variable `total` is initialized to 0 to accumulate the sum.
3. **Loop Through Range**: Using a for loop from 0 to `n` (inclusive), each number is added to `total`.
4. **Printing Result**: After the loop completes, `total` contains the sum of all integers from 0 to `n`, which is then printed.

This method ensures that we efficiently compute the required sum using a linear approach, making it both time and space efficient.

import litellm 
messages = [{"role": "user", "content": "Hey, how's it going"}]

response = litellm.completion(
            model="hosted_vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", # pass the vllm model name
            messages=messages,
            api_base="http://localhost:9000/v1",
            temperature=0.1,
            max_tokens=800)

print(response)

ModelResponse(id='chatcmpl-ab52d2df07df45d09e19039af09d9ee9', created=1740673222, model='hosted_vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B', object='chat.completion', system_fingerprint=None, choices=[Choices(finish_reason='stop', index=0, message=Message(content='Okay, so I just saw this message: "Hey, how\'s it going?" and I\'m trying to figure out what the user is asking for. Let me break it down.\n\nFirst, the greeting is pretty straightforward—Hello. But then, the user is asking, "how\'s it going?" That\'s a common question, but it\'s a bit vague. I need to understand what they\'re really looking for. Maybe they\'re just checking in, or perhaps they\'re seeking some information.\n\nI should consider different angles. Maybe they\'re asking about their day, their work, or something else. Since the user didn\'t specify, I can\'t be sure. But I can think of a few possibilities.\n\n1. **General Well-being**: They might be asking how they\'re feeling in general. That could be for a friend, family member, or someone they\'re meeting online.\n\n2. **Work or Personal Life**: If they\'re talking about work, they might be asking about their current tasks, progress, or any issues they\'re facing. If it\'s personal, they could be discussing hobbies, goals, or stress.\n\n3. **Specific Topics**: They might be asking about a particular subject, like their career, health, or something else. Without more context, it\'s hard to pin down.\n\n4. **Social Interaction**: They could be asking about their online presence, whether they\'re active, or if they\'re looking for advice.\n\nI should also think about the tone. The user used "Hey, how\'s it going?" which is casual and friendly. So, they might be looking for a light-hearted response or just a simple confirmation.\n\nAnother angle is that they might be testing if I\'m paying attention or if I\'m just responding to a generic message. But since they\'re asking a question, it\'s more likely they\'re seeking information.\n\nI wonder if they\'re planning to ask something else in the future. Maybe they\'re just curious and want to know more. Or perhaps they\'re looking for a prompt to start a conversation.\n\nTo sum up, without more context, I can\'t be certain, but I can offer a few possibilities. I should ask them to clarify or provide more details so I can assist them better.\n</think>\n\nIt seems like you\'re asking how you\'re doing, which is a common way to check in. To help you better, could you please clarify what you need assistance with? Whether it\'s for a specific topic, a question, or something else, I\'m here to help!', role='assistant', tool_calls=None, function_call=None, provider_specific_fields={'refusal': None}))], usage=Usage(completion_tokens=510, prompt_tokens=11, total_tokens=521, completion_tokens_details=None, prompt_tokens_details=None), service_tier=None, prompt_logprobs=None)

from crewai import LLM

llm = LLM(
    model="hosted_vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
    temperature=0.2,
    base_url="http://localhost:9000/v1",
    api_key="NA"
)

from crewai import Agent, Task, Crew

# Create a CrewAI agent
agent = Agent(
    role="Researcher",
    goal="Analyze the latest AI trends",
    backstory="An AI expert who gathers and summarizes key insights",
    llm=llm
)

# Define a task with expected_output
task = Task(
    description="Find the top 3 AI trends of 2025.",
    agent=agent,
    expected_output="A list of three key AI trends for 2025 with a brief summary of each."
)

crew = Crew(agents=[agent], tasks=[task])
crew.kickoff()

CrewOutput(raw="1. Generative AI: This trend involves AI systems that can create new content, such as images, text, and music. These systems, often referred to as GANs (Generative Adversarial Networks), are gaining sophistication and are expected to remain relevant in 2025, offering a wide range of applications from art to entertainment.\n\n2. Medical AI: The integration of AI with healthcare is a significant trend. AI is being utilized for diagnostics, drug discovery, and personalized treatment plans. This shift aims to improve healthcare outcomes and efficiency, making AI a cornerstone of modern medical practice.\n\n3. AI Integration with Other Technologies: This trend focuses on enhancing AI's capabilities by integrating it with other technologies, such as robotics and autonomous vehicles. By improving AI's efficiency and adaptability, it can support advancements in manufacturing and other industries, driving innovation and efficiency.\n\nThese trends highlight the transformative potential of AI across various sectors, shaping the future of technology and society.", pydantic=None, json_dict=None, tasks_output=[TaskOutput(description='Find the top 3 AI trends of 2025.', name=None, expected_output='A list of three key AI trends for 2025 with a brief summary of each.', summary='Find the top 3 AI trends of 2025....', raw="1. Generative AI: This trend involves AI systems that can create new content, such as images, text, and music. These systems, often referred to as GANs (Generative Adversarial Networks), are gaining sophistication and are expected to remain relevant in 2025, offering a wide range of applications from art to entertainment.\n\n2. Medical AI: The integration of AI with healthcare is a significant trend. AI is being utilized for diagnostics, drug discovery, and personalized treatment plans. This shift aims to improve healthcare outcomes and efficiency, making AI a cornerstone of modern medical practice.\n\n3. AI Integration with Other Technologies: This trend focuses on enhancing AI's capabilities by integrating it with other technologies, such as robotics and autonomous vehicles. By improving AI's efficiency and adaptability, it can support advancements in manufacturing and other industries, driving innovation and efficiency.\n\nThese trends highlight the transformative potential of AI across various sectors, shaping the future of technology and society.", pydantic=None, json_dict=None, agent='Researcher', output_format=<OutputFormat.RAW: 'raw'>)], token_usage=UsageMetrics(total_tokens=1964, prompt_tokens=469, cached_prompt_tokens=0, completion_tokens=1495, successful_requests=2))

curl -s https://ngrok-agent.s3.amazonaws.com/ngrok.asc | sudo tee /etc/apt/trusted.gpg.d/ngrok.asc >/dev/null && \
echo "deb https://ngrok-agent.s3.amazonaws.com buster main" | sudo tee /etc/apt/sources.list.d/ngrok.list && \
sudo apt update && sudo apt install ngrok

!ngrok config add-authtoken <your_token>

Authtoken saved to configuration file: /home/mohsen/.config/ngrok/ngrok.yml

from pyngrok import ngrok

port = 9000
# Open a ngrok tunnel to the HTTP server
public_url = ngrok.connect(port).public_url
print(f" * ngrok tunnel \"{public_url}\" -> \"http://127.0.0.1:{port}\"")

 * ngrok tunnel "https://8fb3-84-104-50-150.ngrok-free.app" -> "http://127.0.0.1:9000"

llm = LLM(
    model="hosted_vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
    temperature=0.6,
    base_url="https://8fb3-84-104-50-150.ngrok-free.app/v1",
    api_key="NA"
)

from crewai import Agent, Task, Crew

# Create a CrewAI agent
agent = Agent(
    role="Researcher",
    goal="Analyze the latest AI trends",
    backstory="An AI expert who gathers and summarizes key insights",
    llm=llm
)

# Define a task with expected_output
task = Task(
    description="Find the top 3 AI trends of 2025.",
    agent=agent,
    expected_output="A list of three key AI trends for 2025 with a brief summary of each."
)

crew = Crew(agents=[agent], tasks=[task])
crew.kickoff()

Overriding of current TracerProvider is not allowed

CrewOutput(raw='The top three AI trends for 2025 are:  \n1. Generative AI: advancing in alignment with human intent to aid decision-making and understanding, enhancing image generation beyond mere creation.  \n2. AI in Sustainability: contributing to climate modeling, resource management, and healthcare through smarter grids and supply chain optimization, with a focus on ethical AI.  \n3. Ethical AI: driving responsible applications in education, mental health, and criminal justice, with a trend towards better ethical AI and accountability.', pydantic=None, json_dict=None, tasks_output=[TaskOutput(description='Find the top 3 AI trends of 2025.', name=None, expected_output='A list of three key AI trends for 2025 with a brief summary of each.', summary='Find the top 3 AI trends of 2025....', raw='The top three AI trends for 2025 are:  \n1. Generative AI: advancing in alignment with human intent to aid decision-making and understanding, enhancing image generation beyond mere creation.  \n2. AI in Sustainability: contributing to climate modeling, resource management, and healthcare through smarter grids and supply chain optimization, with a focus on ethical AI.  \n3. Ethical AI: driving responsible applications in education, mental health, and criminal justice, with a trend towards better ethical AI and accountability.', pydantic=None, json_dict=None, agent='Researcher', output_format=<OutputFormat.RAW: 'raw'>)], token_usage=UsageMetrics(total_tokens=2013, prompt_tokens=469, cached_prompt_tokens=0, completion_tokens=1544, successful_requests=2))

Use Case	Best Choice
Fast, efficient inference	✅ vLLM
Training & fine-tuning	✅ Hugging Face Transformers
Experimentation & prototyping	✅ Hugging Face Transformers
Running large models efficiently	✅ vLLM

Running DeepSeek R1 Locally with vLLM and Ray Dashboard¶

vLLM vs Hugging Face Transformers: Which One to Use for Running Models Locally?¶

When to Use vLLM¶

When to Use Hugging Face Transformers¶

Summary¶

Setup Process¶

1. Create and Activate a Virtual Environment¶

2. Install Dependencies¶

3. Start Jupyter Notebook¶

Next Steps¶

Accessing the Ray Dashboard¶

Ngrok auth¶

1️⃣What is ngrok?¶

2️⃣Why Should You Use ngrok?¶

Exposing Localhost to the Internet¶

Testing Webhooks¶

Remote Access to Jupyter Notebooks¶

Collaboration & Demos¶

Bypassing Firewalls & NAT¶

3️⃣How to Install and Use ngrok¶

** Install ngrok (for WSL/Ubuntu) if not installed*¶

Authenticate ngrok¶

Expose a Local Server¶

4️⃣Security Reminder¶

5️⃣Should You Use ngrok?¶