Introduction

Mixtral-8x7B is a Sparse Mixture of Experts (SMoE) with 46.7B parameters and one of the best open large language models (LLM). Mixtral was trained with a context size of 32k tokens and it outperforms or matches Llama-2 70B and GPT-3.5 across all evaluated benchmarks. Mixtral and Mistral 7B share the same structure, but Mixtral’s layers consist of 8 feedforward blocks or experts. In each layer, a router network chooses two experts to handle the current state of a token and merges their outputs. Although each token interacts with only two experts, the chosen ones can vary at each step. This design allows each token to access a total of 47B parameters, yet during inference, only 13B of these parameters are actively utilized.

Our Observations

We experimented Mixtral 8x7B with various configurations using PyTorch, vLLM, AutoGPTQ, and HQQ. For all our experiments, we have set the max-token to 256 and done all experiments on a single A100(80GB) GPU machine.

For fast inference, we took advantage of PyTorch(nightly) optimizations (GitHub repository). We have deployed an 8-bit quantize model and got an average token generation rate of 52.03 token/sec. We also tried deploying a 4-bit quantized model via vLLM(0.2.7), Auto-GPTQ(0.6.0) and HQQ(0.1.2) as mentioned in our observations below:

LibraryBitsInference TimeCold Start TimeToken/SecLatency/TokenVRAM Required
PyTorch8 bit4.94 sec11.48 sec52.0319.22 ms43.78 GB
vLLM4 bit6.59 sec36.62 sec36.3927.47 ms65.66 GB
AutoGPTQ4 bit38.44 sec203.45 sec7.11140.76 ms22.68 GB
HQQ4 bit255.09 sec16.19 sec5.16193.47 ms24.70 GB

Defining Dependencies

We are using gpt-fast(GitHub repository from PyTorch Labs), written in native PyTorch. Install the PyTorch nightly, Sentencepiece and Huggingface_hub.

Constructing the GitHub/GitLab Template

First, to quickly construct the GitHub/GitLab template, copy all the files from this Inferless repository. After that, you can create the app.py and inferless-runtime-config.yaml.

Mixtral-8x7B/
├── app.py
├── GPTQ.py
├── _model.py
├── eval.py
├── generate.py
├── get_model.py
├── quantize.py
├── tp.py
├── input_schema.py
└── inferless-runtime-config.yaml

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 download and initialize your model. Here we have used the model_initialize function from the get_model script, this loads and initialize the model. You can customize the get_model script according to your requirements. Also in this function, you can 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) parameters.

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

import contextlib
from get_model import model_initialize,encode_tokens,generate
from huggingface_hub import snapshot_download
import os

class InferlessPythonModel:
    def initialize(self):
        repo_id = "Inferless/Mixtral-8x7B-v0.1-int8-GPTQ"
        model_store = f"/home/{repo_id}"
        os.makedirs(f"/home/{repo_id}", exist_ok=True)
        snapshot_download(repo_id,local_dir=model_store)
        self.tokenizer, self.model = model_initialize(f"{model_store}/model_int8.pth")
        self.callback = lambda x : x

    def infer(self, inputs):
        prompt= inputs['prompt']
        encoded = encode_tokens(self.tokenizer,prompt, bos=True, device="cuda")
        prof = contextlib.nullcontext()
        with prof:
            y, metrics = generate(
                    self.model,
                    encoded,
                    max_new_tokens=256,
                    draft_model=None,
                    speculate_k=5,
                    interactive=False,
                    callback=self.callback,
                    temperature=0.8,
                    top_k=200,)

        return {'generated_result': self.tokenizer.decode(y.tolist())}

    def finalize(self):
        pass

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"
  system_packages:
    - "libssl-dev"
  python_packages:
    - "--index-url https://download.pytorch.org/whl/nightly/cu121--pre torch"
    - "torchvision"
    - "torchaudio"
    - "sentencepiece==0.1.99"
    - "huggingface-hub==0.20.2"
    - "accelerate==0.25.0"

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