Go to file
Ryan Voots ced04e1dff disable the error exit here, see if the pregen code works 2023-10-26 12:43:07 -04:00
.github fix powershell (#284) 2023-08-24 23:53:07 +09:00
auto_gptq Merge remote-tracking branches 'laaza/Mistral' and 'laaza/MPT' 2023-10-22 07:53:59 -04:00
autogptq_extension Generated files so that when they fail to work in pipeline then it still continues with what should be some ok defaults 2023-10-26 10:26:42 -04:00
docs update README 2023-08-24 21:16:04 +08:00
examples Removed unexpected file that shouldn't have been added, sorry 2023-09-06 18:08:30 +01:00
tests exllamav2 integration 2023-09-25 16:51:18 +00:00
.gitignore add conda cuda include directory if found 2023-05-05 14:27:11 -04:00
LICENSE Initial commit 2023-04-13 10:18:11 +08:00
README.md update README 2023-09-25 18:55:34 +08:00
README_zh.md update README 2023-09-25 18:55:34 +08:00
qigen.tar.xz Built locally for temp setup, not sure what its doing but it is doing weird stuff on build server, like it never determines something 2023-10-26 10:26:13 -04:00
setup.py disable the error exit here, see if the pregen code works 2023-10-26 12:43:07 -04:00



An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

GitHub release PyPI - Downloads

English | 中文

The path to v1.0.0

Hi, fellow community members, long time no see! I'm sorry that I haven't been able to update this project more frequently due to personal reasons during this period. The past few weeks have been huge in terms of my career plans. Not long ago, I officially bid farewell to the startup team that I joined for two years after graduation. I'm very grateful to the leaders and colleagues of the team for their trust and guidance, which enabled me to grow rapidly in two years; at the same time, I'm also really grateful to the team for allowing me to use the internal A100 GPU server cluster free of charge since the start of the AutoGPTQ project to complete various experiments and performance evaluations. (Of course, it can no longer be used in the future, so it will mean a lot to me if there will be new hardware sponsorship!) In the past two years, I have served as an AI engineer in this team, responsible for the LLM based dialogue system's architecture design and develop. We had successfully launched a product called gemsouls, but unfortunately it has ceased operations. Now, the team is about to launch a new product called modelize, which is a LLM-native AI agent platform, where users can use multiple AI agents to build a highly automated team, allowing them to interact with each other in the workflow, collaborate to complete complex projects efficiently.

Getting back to the topic, I'm very excited to see that in the past few months, research on optimizing the inference performance of LLMs has made tremendous progress. Now we can not only complete the inference of LLMs on high-end GPUs efficiently, but also on CPUs and even edge devices. A series of technological advancements make me eager to make more contributions to the open source community. Therefore, I will first use about four weeks to gradually update AutoGPTQ to the v1.0.0 official version. During this period, there will also be 2~3 minor versions are released to allow users to experience performance optimization and new features timely. In my vision, by the time v1.0.0 is officially released, AutoGPTQ will be able to serve as an extendable and flexible quantization backend that supports all GPTQ-like methods and automatically quantize LLMs written by Pytorch. I detailed the development plan in this issue, feel free to drop in there for discussion and give your suggestions!

News or Update

  • 2023-08-23 - (News) - 🤗 Transformers, optimum and peft have integrated auto-gptq, so now running and training GPTQ models can be more available to everyone! See this blog and it's resources for more details!
  • 2023-08-21 - (News) - Team of Qwen officially released 4bit quantized version of Qwen-7B based on auto-gptq, and provided a detailed benchmark results
  • 2023-08-06 - (Update) - Support exllama's q4 CUDA kernel to have at least 1.3x speed up for int4 quantized models when doing inference.
  • 2023-08-04 - (Update) - Support RoCm so that AMD GPU users can use auto-gptq with CUDA extensions.
  • 2023-07-26 - (Update) - An elegant PPL benchmark script to get results that can be fairly compared with other libraries such as llama.cpp.
  • 2023-06-05 - (Update) - Integrate with 🤗 peft to use gptq quantized model to train adapters, support LoRA, AdaLoRA, AdaptionPrompt, etc.
  • 2023-05-30 - (Update) - Support download/upload quantized model from/to 🤗 Hub.

For more histories please turn to here

Performance Comparison

Inference Speed

The result is generated using this script, batch size of input is 1, decode strategy is beam search and enforce the model to generate 512 tokens, speed metric is tokens/s (the larger, the better).

The quantized model is loaded using the setup that can gain the fastest inference speed.

model GPU num_beams fp16 gptq-int4
llama-7b 1xA100-40G 1 18.87 25.53
llama-7b 1xA100-40G 4 68.79 91.30
moss-moon 16b 1xA100-40G 1 12.48 15.25
moss-moon 16b 1xA100-40G 4 OOM 42.67
moss-moon 16b 2xA100-40G 1 06.83 06.78
moss-moon 16b 2xA100-40G 4 13.10 10.80
gpt-j 6b 1xRTX3060-12G 1 OOM 29.55
gpt-j 6b 1xRTX3060-12G 4 OOM 47.36


For perplexity comparison, you can turn to here and here


Quick Installation

You can install the latest stable release of AutoGPTQ from pip with pre-built wheels compatible with PyTorch 2.0.1:

  • For CUDA 11.7: pip install auto-gptq
  • For CUDA 11.8: pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
  • For RoCm 5.4.2: pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/rocm542/

Warning: These wheels are not expected to work on PyTorch nightly. Please install AutoGPTQ from source when using PyTorch nightly.

AutoGPTQ can be installed with the Triton dependency with pip install auto-gptq[triton] in order to be able to use the Triton backend (currently only supports linux, no 3-bits quantization).

Install from source

Clone the source code:

git clone https://github.com/PanQiWei/AutoGPTQ.git && cd AutoGPTQ

Then, install from source:

pip install -v .

You can set BUILD_CUDA_EXT=0 to disable pytorch extension building, but this is strongly discouraged as AutoGPTQ then falls back on a slow python implementation.

To install from source for AMD GPUs supporting RoCm, please specify the ROCM_VERSION environment variable. The compilation can be speeded up by specifying the PYTORCH_ROCM_ARCH variable (reference), for example gfx90a for MI200 series devices. Example:

ROCM_VERSION=5.6 pip install -v .

For RoCm systems, the packages rocsparse-dev, hipsparse-dev, rocthrust-dev, rocblas-dev and hipblas-dev are required to build.

Quick Tour

Quantization and Inference

warning: this is just a showcase of the usage of basic apis in AutoGPTQ, which uses only one sample to quantize a much small model, quality of quantized model using such little samples may not good.

Below is an example for the simplest use of auto_gptq to quantize a model and inference after quantization:

from transformers import AutoTokenizer, TextGenerationPipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import logging

    format="%(asctime)s %(levelname)s [%(name)s] %(message)s", level=logging.INFO, datefmt="%Y-%m-%d %H:%M:%S"

pretrained_model_dir = "facebook/opt-125m"
quantized_model_dir = "opt-125m-4bit"

tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
examples = [
        "auto-gptq is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm."

quantize_config = BaseQuantizeConfig(
    bits=4,  # quantize model to 4-bit
    group_size=128,  # it is recommended to set the value to 128
    desc_act=False,  # set to False can significantly speed up inference but the perplexity may slightly bad

# load un-quantized model, by default, the model will always be loaded into CPU memory
model = AutoGPTQForCausalLM.from_pretrained(pretrained_model_dir, quantize_config)

# quantize model, the examples should be list of dict whose keys can only be "input_ids" and "attention_mask"

# save quantized model

# save quantized model using safetensors
model.save_quantized(quantized_model_dir, use_safetensors=True)

# push quantized model to Hugging Face Hub.
# to use use_auth_token=True, Login first via huggingface-cli login.
# or pass explcit token with: use_auth_token="hf_xxxxxxx"
# (uncomment the following three lines to enable this feature)
# repo_id = f"YourUserName/{quantized_model_dir}"
# commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"
# model.push_to_hub(repo_id, commit_message=commit_message, use_auth_token=True)

# alternatively you can save and push at the same time
# (uncomment the following three lines to enable this feature)
# repo_id = f"YourUserName/{quantized_model_dir}"
# commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"
# model.push_to_hub(repo_id, save_dir=quantized_model_dir, use_safetensors=True, commit_message=commit_message, use_auth_token=True)

# load quantized model to the first GPU
model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device="cuda:0")

# download quantized model from Hugging Face Hub and load to the first GPU
# model = AutoGPTQForCausalLM.from_quantized(repo_id, device="cuda:0", use_safetensors=True, use_triton=False)

# inference with model.generate
print(tokenizer.decode(model.generate(**tokenizer("auto_gptq is", return_tensors="pt").to(model.device))[0]))

# or you can also use pipeline
pipeline = TextGenerationPipeline(model=model, tokenizer=tokenizer)
print(pipeline("auto-gptq is")[0]["generated_text"])

For more advanced features of model quantization, please reference to this script

Customize Model

Below is an example to extend `auto_gptq` to support `OPT` model, as you will see, it's very easy:
from auto_gptq.modeling import BaseGPTQForCausalLM

class OPTGPTQForCausalLM(BaseGPTQForCausalLM):
    # chained attribute name of transformer layer block
    layers_block_name = "model.decoder.layers"
    # chained attribute names of other nn modules that in the same level as the transformer layer block
    outside_layer_modules = [
        "model.decoder.embed_tokens", "model.decoder.embed_positions", "model.decoder.project_out",
        "model.decoder.project_in", "model.decoder.final_layer_norm"
    # chained attribute names of linear layers in transformer layer module
    # normally, there are four sub lists, for each one the modules in it can be seen as one operation,
    # and the order should be the order when they are truly executed, in this case (and usually in most cases),
    # they are: attention q_k_v projection, attention output projection, MLP project input, MLP project output
    inside_layer_modules = [
        ["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj"],

After this, you can use OPTGPTQForCausalLM.from_pretrained and other methods as shown in Basic.

Evaluation on Downstream Tasks

You can use tasks defined in auto_gptq.eval_tasks to evaluate model's performance on specific down-stream task before and after quantization.

The predefined tasks support all causal-language-models implemented in 🤗 transformers and in this project.

Below is an example to evaluate `EleutherAI/gpt-j-6b` on sequence-classification task using `cardiffnlp/tweet_sentiment_multilingual` dataset:
from functools import partial

import datasets
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from auto_gptq.eval_tasks import SequenceClassificationTask

MODEL = "EleutherAI/gpt-j-6b"
DATASET = "cardiffnlp/tweet_sentiment_multilingual"
TEMPLATE = "Question:What's the sentiment of the given text? Choices are {labels}.\nText: {text}\nAnswer:"
    0: "negative",
    1: "neutral",
    2: "positive"
LABELS = list(ID2LABEL.values())

def ds_refactor_fn(samples):
    text_data = samples["text"]
    label_data = samples["label"]

    new_samples = {"prompt": [], "label": []}
    for text, label in zip(text_data, label_data):
        prompt = TEMPLATE.format(labels=LABELS, text=text)

    return new_samples

#  model = AutoModelForCausalLM.from_pretrained(MODEL).eval().half().to("cuda:0")
model = AutoGPTQForCausalLM.from_pretrained(MODEL, BaseQuantizeConfig())
tokenizer = AutoTokenizer.from_pretrained(MODEL)

task = SequenceClassificationTask(
            "num_samples": 1000,  # how many samples will be sampled to evaluation
            "sample_max_len": 1024,  # max tokens for each sample
            "block_max_len": 2048,  # max tokens for each data block
            # function to load dataset, one must only accept data_name_or_path as input
            # and return datasets.Dataset
            "load_fn": partial(datasets.load_dataset, name="english"),
            # function to preprocess dataset, which is used for datasets.Dataset.map,
            # must return Dict[str, list] with only two keys: [prompt_col_name, label_col_name]
            "preprocess_fn": ds_refactor_fn,
            # truncate label when sample's length exceed sample_max_len
            "truncate_prompt": False

# note that max_new_tokens will be automatically specified internally based on given classes

# self-consistency

Learn More

tutorials provide step-by-step guidance to integrate auto_gptq with your own project and some best practice principles.

examples provide plenty of example scripts to use auto_gptq in different ways.

Supported Models

you can use model.config.model_type to compare with the table below to check whether the model you use is supported by auto_gptq.

for example, model_type of WizardLM, vicuna and gpt4all are all llama, hence they are all supported by auto_gptq.

model type quantization inference peft-lora peft-ada-lora peft-adaption_prompt
gpt_neox requires this peft branch
gptj requires this peft branch
moss requires this peft branch

Supported Evaluation Tasks

Currently, auto_gptq supports: LanguageModelingTask, SequenceClassificationTask and TextSummarizationTask; more Tasks will come soon!

Running tests

Tests can be run with:

pytest tests/ -s


  • Specially thanks Elias Frantar, Saleh Ashkboos, Torsten Hoefler and Dan Alistarh for proposing GPTQ algorithm and open source the code.
  • Specially thanks qwopqwop200, for code in this project that relevant to quantization are mainly referenced from GPTQ-for-LLaMa.

Star History Chart