Activation-aware Weight Quantization (AWQ): Unlocking LLM Efficiency—Part 2: Benchmarks and Practical Guide

As mentioned in our previous article, Activation-Aware Weight Quantization (AWQ) is a technique that optimizes the efficiency of a neural network without compromising its accuracy. Unlike traditional weight quantization methods, AWQ leverages a deep understanding of the data distribution within neural networks during inference. In the calibration phase, it collects statistics on the specific activations a model generates when exposed to input data. These statistics enable the precise determination of quantization parameters, such as scale and offset, tailored to the data distribution.

AWQ strikes a harmonious balance between model efficiency and accuracy, making it an invaluable tool for deploying LLMs efficiently. What’s more, running AWQ-ed models is made seamless with Friendli Inference, a powerful LLM serving engine from FriendliAI. For example, one can run AWQ-ed LLMs (e.g., Llama 2 70B 4-bit on a single A100 80 GB GPU) natively on Friendli Inference.

Benchmark Accuracy Numbers: Unlocking the Potential of AWQ on Friendli Inference

The accuracy of AWQ-ed models on Friendli Inference is remarkable. We run the following benchmark tests with Llama-2–13b-chat (meta-llama/Llama-2–13b-chat-hf in Hugging Face).

As you can see, the 4bit AWQ-ed Llama-2–13b-chat model running on Friendli Inference shows similar performance to the original Llama-2–13b-chat model. These results underscore the effectiveness of AWQ-ed models running on Friendli Inference in maintaining or even improving model accuracy while significantly reducing the memory and computational requirements.

Running AWQ-ed Models on Friendli Inference: A Step-by-Step Guide

1. Converting an Unquantized Model: To harness the power of AWQ, begin by converting your unquantized model to its quantized counterpart using the following commands:

   The content of file specified at $QUANT_CONFIG_FILE is as follows:

   This step ensures that your model is quantized using AWQ to reduce the model size for efficiency while preserving its accuracy.

2. Running Friendli Inference: Once you have the quantized model checkpoint, load it into Friendli Inference, the versatile serving engine from FriendliAI.

   With the provided commands, Friendli Inference provides a seamless and efficient environment for serving your AWQ-ed models.

3. Sending Inference Requests to the AWQ-ed model on Friendli Inference: With Friendli Inference up and running, you can now send inference requests to the server.

   Friendli Inference takes care of the heavy lifting, delivering high-performance inference serving while sparing you the complexities of deployment.

Stay Tuned for our Performance Numbers!

Running LLMs with AWQ on Friendli Inference enables users to achieve efficient LLM deployment. This powerful feature achieves remarkable efficiency gains without sacrificing accuracy. Stay tuned for our next article, where we’ll discuss performance that demonstrates the true potential of AWQ-ed models on Friendli Inference.