Introduction

Qwen2-72B-Instruct is a part of the latest series of Qwen2 large language models, featuring base and instruction-tuned models ranging from 0.5 to 72 billion parameters, expanding language support to 29 languages. These models showcase state-of-the-art performance across various benchmarks, with significant improvements in coding and mathematical tasks. Notably, the 7B and 72B instruction-tuned versions support an impressive 128K token context length, pushing the boundaries of large language model capabilities.

Our Observations

We have deployed the model on an A100 GPU(80GB). Here are our observations:

LibraryInference TimeCold Start TimeTokens/SecOutput Tokens Length
vLLM24.79 sec35.59 sec17.83512

Note: The inference time, cold start time, and tokens per second are average values.

Defining Dependencies

We are using the vLLM to serve the model on a single A100 (80GB).

Constructing the GitHub/GitLab Template

Now quickly construct the GitHub/GitLab template, this process is mandatory and make sure you don’t add any file named model.py.

Qwen2-72B-Instruct/
├── app.py
├── inferless-runtime-config.yaml
├── inferless.yaml
└── input_schema.py

You can also add other files to this directory.

Create the class for inference

In the app.py we will define the class and import all the required functions

  1. def initialize: In this function, you will initialize your model and define any variable that you want to use during inference.

  2. def infer: This function gets called for every request that you send. Here you can define all the steps that are required for the inference. You can also pass custom values for inference and pass it through inputs(dict) parameter.

  3. def finalize: This function cleans up all the allocated memory.

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

class InferlessPythonModel:

    def initialize(self):
        model_id = "Qwen/Qwen2-72B-Instruct-AWQ"  # Specify the model repository ID
        # Initialize the LLM object with the downloaded model directory
        self.llm = LLM(model=model_id, enforce_eager=True, quantization="AWQ")
        
        # Load the tokenizer associated with the pre-trained model
        self.tokenizer = AutoTokenizer.from_pretrained(model_id)

    def infer(self, inputs):
        prompts = inputs["prompt"]  # Extract the prompt from the input
        temperature = inputs.get("temperature",0.7)
        top_p = inputs.get("top_p",0.1)
        repetition_penalty = inputs.get("repetition_penalty",1.18)
        top_k = inputs.get("top_k",40)
        max_tokens = inputs.get("max_tokens",512)

        # Define sampling parameters for model generation
        sampling_params = SamplingParams(temperature=temperature,top_p=top_p,repetition_penalty=repetition_penalty,
                                         top_k=top_k,max_tokens=max_tokens)
        # Apply the chat template and convert to a list of strings (without tokenization)
        input_text = self.tokenizer.apply_chat_template([{"role": "user", "content": prompts}], tokenize=False)

        # Generate text using the LLM with the specified sampling parameters
        result = self.llm.generate(input_text, sampling_params)

        # Extract the generated text from the result object
        result_output = [output.outputs[0].text for output in result]

        # Return a dictionary containing the generated text
        return {"generated_result": result_output[0]}

    def finalize(self):
        self.llm = None

Create the Input Schema

We have to create a input_schema.py in your GitHub/Gitlab repository this will help us create the Input parameters. You can checkout our documentation on Input / Output Schema.

For this tutorial, we have defined these parameter prompt, temperature, top_p, repetition_penalty, max_tokens and top_k which are required during the API call. Now lets create the input_schema.py.

INPUT_SCHEMA = {
    "prompt": {
        'datatype': 'STRING',
        'required': True,
        'shape': [1],
        'example': ["What is deep meaning?"]
    },
    "temperature": {
        'datatype': 'FP32',
        'required': False,
        'shape': [1],
        'example': [0.7]
    },
    "top_p": {
        'datatype': 'FP32',
        'required': False,
        'shape': [1],
        'example': [0.1]
    },
    "repetition_penalty": {
        'datatype': 'FP32',
        'required': False,
        'shape': [1],
        'example': [1.18]
    },
    "max_tokens": {
        'datatype': 'INT16',
        'required': False,
        'shape': [1],
        'example': [512]
    },
    "top_k":{
        'datatype': 'INT8',
        'required': False,
        'shape': [1],
        'example': [40]
    }
}

Creating the Custom Runtime

This is a mandatory step where we allow the users to upload their custom runtime through inferless-runtime-config.yaml.

build:
  python_packages:
    - "transformers==4.41.2"
    - "vllm==0.5.0.post1"

Method A: Deploying the model on Inferless Platform

Inferless supports multiple ways of importing your model. For this tutorial, we will use GitHub.

Step 1: Login to the inferless dashboard can click on Import model button

Navigate to your desired workspace in Inferless and Click on Add a custom model button that you see on the top right. An import wizard will open up.

Step 2: Follow the UI to complete the model Import

  • Select the GitHub/GitLab Integration option to connect your source code repository with the deployment environment.
  • Navigate to the specific GitHub repository that contains your model’s code. Here, you will need to identify and enter the name of the model you wish to import.
  • Choose the appropriate type of machine that suits your model’s requirements. Additionally, specify the minimum and maximum number of replicas to define the scalability range for deploying your model.
  • Optionally, you have the option to enable automatic build and deployment. This feature triggers a new deployment automatically whenever there is a new code push to your repository.
  • If your model requires additional software packages, configure the Custom Runtime settings by including necessary pip or apt packages. Also, set up environment variables such as Inference Timeout, Container Concurrency, and Scale Down Timeout to tailor the runtime environment according to your needs.
  • Wait for the validation process to complete, ensuring that all settings are correct and functional. Once validation is successful, click on the “Import” button to finalize the import of your model.

Step 3: Wait for the model build to complete usually takes ~5-10 minutes

Step 4: Use the APIs to call the model

Once the model is in ‘Active’ status you can click on the ‘API’ page to call the model

Here is the Demo:

Method B: Deploying the model on Inferless CLI

Inferless allows you to deploy your model using Inferless-CLI. Follow the steps to deploy using Inferless CLI.

Initialization of the model

Create the app.py and inferless-runtime-config.yaml, move the files to the working directory. Run the following command to initialize your model:

inferless init

Upload the custom runtime

Once you have created the inferless-runtime-config.yaml file, you can run the following command:

inferless runtime upload

Upon entering this command, you will be prompted to provide the configuration file name. Enter the name and ensure to update it in the inferless.yaml file. Now you are ready for the deployment.

Deploy the Model

Execute the following command to deploy your model. Once deployed, you can track the build logs on the Inferless platform:

inferless deploy