Deploy CodeLlama 70B using Inferless

Introduction

Code Llama 70B, a pre-trained and fine-tuned generative text model, excels in understanding and generating code with a HumanEval score of 67.8, surpassing GPT-4. It’s based on Llama 2’s architecture, trained on 500B tokens, and is commercially available, catering to diverse applications with its advanced code generation abilities.

Our Observations

We have deployed the 4-bit quantized version of the model using vLLM on an A100 GPU(80GB). Here are our observations:

Inference Time	Cold Start Time	Token/Sec	Latency/Token	VRAM Required
6.67 sec	26.36 sec	33.18	30.13 ms	37.05 GB

Defining Dependencies

We are using the vLLM library, which boost the inference speed of you LLM. We will deploy a GPTQ 4bit quantized version of the model.

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.

CodeLlama-70B/
├── 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

def initialize: In this function, you will initialize your model and define any variable that you want to use during inference. You can adjust the gpu_memory_utilization parameter to reduce GPU usage. By default, it’s set to 0.9, but you can change it to 0.5 to decrease GPU utilization to 37.05 GB.
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.
def finalize: This function cleans up all the allocated memory.

from vllm import LLM, SamplingParams
import inferless

app = inferless.Cls(gpu="A100")

class InferlessPythonModel:
    @app.load
    def initialize(self):
        model_id = "TheBloke/CodeLlama-70B-Python-GPTQ"
        self.sampling_params = SamplingParams(temperature=0.7, top_p=0.95,max_tokens=256)
        self.llm = LLM(model=model_id, quantization="gptq", dtype="float16",gpu_memory_utilization=0.5)

    @app.infer
    def infer(self, inputs):
        prompts = inputs["prompt"]
        result = self.llm.generate(prompts, self.sampling_params)
        result_output = [output.outputs[0].text for output in result]

        return {'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 a parameter prompt which is required during the API call. Now lets create the input_schema.py.

INPUT_SCHEMA = {
    "prompt": {
        'datatype': 'STRING',
        'required': True,
        'shape': [1],
        'example': ["def factorial(int n):"]
    }
}

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:
  cuda_version: "12.1.1"
  python_packages:
    - "vllm==0.6.3.post1"
    - "inferless-cli==2.0.9"
    - "hf-transfer==0.1.9"
    - "huggingface-hub==0.27.1"

Test your model with Remote Run

You can use the inferless remote-run(installation guide here) command to test your model or any custom Python script in a remote GPU environment directly from your local machine. Make sure that you use Python3.10 for seamless experience.

Step 1: Add the Decorators and local entry point

To enable Remote Run, simply do the following:

Import the inferless library and initialize Cls(gpu="A100"). The available GPU options are T4, A10 and A100.
Decorated the initialize and infer functions with @app.load and @app.infer respectively.
Create the Local Entry Point by decorating a function (for example, my_local_entry) with @inferless.local_entry_point. Within this function, instantiate your model class, convert any incoming parameters into a RequestObjects object, and invoke the model’s infer method.

from vllm import LLM, SamplingParams
import inferless
from pydantic import BaseModel, Field
from typing import Optional

@inferless.request
class RequestObjects(BaseModel):
    prompt: str = Field(default="def factorial(int n):")
    temperature: Optional[float] = 0.7
    top_p: Optional[float] = 0.1
    repetition_penalty: Optional[float] = 1.18
    top_k: Optional[int] = 40
    max_tokens: Optional[int] = 256

@inferless.response
class ResponseObjects(BaseModel):
    generated_text: str = Field(default='Test output')

app = inferless.Cls(gpu="A100")

class InferlessPythonModel:
    @app.load
    def initialize(self):
        model_id = "TheBloke/CodeLlama-70B-Python-GPTQ"
        self.sampling_params = SamplingParams(temperature=0.7, top_p=0.95,max_tokens=256)
        self.llm = LLM(model=model_id, quantization="gptq", dtype="float16",gpu_memory_utilization=0.5)

    @app.infer
    def infer(self, request: RequestObjects) -> ResponseObjects:
        sampling_params = SamplingParams(temperature=request.temperature,top_p=request.top_p,repetition_penalty=request.repetition_penalty,
                                         top_k=request.top_k,max_tokens=request.max_tokens)
        result = self.llm.generate(request.prompt, sampling_params)
        result_output = [output.outputs[0].text for output in result]

        generateObject = ResponseObjects(generated_text = result_output[0])
        return generateObject

    def finalize(self):
        self.llm = None

@inferless.local_entry_point
def my_local_entry(dynamic_params):
    request_objects = RequestObjects(**dynamic_params)
    model_instance = InferlessPythonModel()

    return model_instance.infer(request_objects)

Step 2: Run with Remote GPU

From your local terminal, navigate to the folder containing your app.py and your inferless-runtime-config.yaml and run:

inferless remote-run app.py -c inferless-runtime-config.yaml --prompt "def factorial(int n):"

You can pass the other input parameters in the same way as long as your code expects them in the inputs dictionary. If you want to exclude certain files or directories from being uploaded, use the --exclude or -e flag.

Method A: Deploying the model on Inferless Platform

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

Clone the repository of the model

Let’s begin by cloning the model repository:

git clone https://github.com/inferless/CodeLlama-70B.git

Deploy the Model

To deploy the model using Inferless CLI, execute the following command:

inferless deploy --gpu A100 --runtime inferless-runtime-config.yaml

Explanation of the Command:

--gpu A100: Specifies the GPU type for deployment. Available options include A10, A100, and T4.
--runtime inferless-runtime-config.yaml: Defines the runtime configuration file. If not specified, the default Inferless runtime is used.

How-to Guides

​Introduction

​Our Observations

​Defining Dependencies

​Constructing the GitHub/GitLab Template

​Create the class for inference

​Create the Input Schema

​Creating the Custom Runtime

​Test your model with Remote Run

​Step 1: Add the Decorators and local entry point

​Step 2: Run with Remote GPU

​Method A: Deploying the model on Inferless Platform

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

​Step 2: Follow the UI to complete the model Import

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

​Step 4: Use the APIs to call the model

​Here is the Demo:

​Method B: Deploying the model on Inferless CLI

​Clone the repository of the model

​Deploy the Model