Skip to main content

A general x-bit quantization engine for LLMs,[2-8] bits, awq/gptq/hqq

Project description

QLLM

Open In Colab GitHub - Releases PyPI - Downloads

Supports any LLMs in HuggingFace/Transformers, mixed bits(2-8bit), GPTQ/AWQ/HQQ, ONNX export

QLLM is a out-of-box quantization toolbox for large language models, It didn't limit to a specific model, and designed to be auto-quantization layer by layer for any LLMs. It can also be used to export quantized model to onnx with only one args `--export_onnx ./onnx_model`, and inference with onnxruntime. Besides, model quantized by different quantization method (GPTQ/AWQ/HQQ) can be loaded from huggingface/transformers and transfor to each other without extra effort.

We alread supported

  • GPTQ quantization
  • AWQ quantization
  • HQQ quantization

Features:

  • GPTQ supports all LLM models in huggingface/transformers, it will automatically detect the model type and quantize it.
  • We support to quantize model by 2-8 bits, and support to quantize model with different quantization bits for different layers.
  • Auto promoting bits/group-size for better accuracy

Latest News 🔥

  • [2024/01] Support HQQ algorithm
  • [2023/12] The first PyPi package released

Installation

Easy to install qllm from PyPi [cu121]

pip install qllm

Install from release package, CUDA-118/121 is supported. [py38, py39, py310] https://github.com/wejoncy/QLLM/releases

Build from Source

Please set ENV EXCLUDE_EXTENTION_FOR_FAST_BUILD=1 for fast build

If you are using CUDA-121

pip install git+https://github.com/wejoncy/QLLM.git

OR CUDA-118/117

git clone https://github.com/wejoncy/QLLM.git
cd QLLM
python setup.py install

How to use it

Quantize llama2

#  Quantize and Save compressed model, method can be one of [gptq/awq/hqq]
python -m qllm --model=meta-llama/Llama-2-7b-hf --method=gptq --nsamples=64 --wbits=4 --groupsize=128 --save ./Llama-2-7b-4bit

(NEW) Quantize model with mix bits/groupsize for higher precision (PPL)

#  Quantize and Save compressed model
python -m qllm --model=meta-llama/Llama-2-7b-hf --method=gptq --save ./Llama-2-7b-4bit --allow_mix_bits --true-sequential

NOTE:

  1. only support GPTQ
  2. allow_mix_bits option refered from gptq-for-llama, QLLM makes it easier to use and flexible
  3. wjat different with gptq-for-llama is we grow bit by one instead of times 2.
  4. all configurations will be saved/load automaticlly instead of quant-table which used by gptq-for-llama.
  5. if --allow_mix_bits is enabled, The saved model is not compatible with vLLM for now.

Quantize model for vLLM

Due to the zereos diff, we need to set a env variable if you set pack_mode to GPTQ whenver the method is awq or gptq

COMPATIBLE_WITH_AUTOGPTQ=1 python -m qllm --model=meta-llama/Llama-2-7b-hf --method=gptq --save ./Llama-2-7b-4bit --pack_mode=GPTQ

If you use GEMM pack_mode, then you don't have to set the var

python -m qllm --model=meta-llama/Llama-2-7b-hf --method=gptq --save ./Llama-2-7b-4bit --pack_mode=GEMM
python -m qllm --model=meta-llama/Llama-2-7b-hf --method=awq --save ./Llama-2-7b-4bit --pack_mode=GEMM

Conversion between AWQ and GPTQ

python -m qllm --load TheBloke/Llama-2-7B-Chat-AWQ --eval --save ./Llama-2-7b-chat-hf_gptq_q4/ --pack_mode=GPTQ

Or you can use --pack_mode=AWQ to convert GPTQ to AWQ.

python -m qllm --load TheBloke/Llama-2-7B-Chat-GPTQ --eval --save ./Llama-2-7b-chat-hf_awq_q4/ --pack_mode=GEMM

Note:

Not all cases are supported, for example,

  1. if you quantized model with different quantization bits for different layers, you can't convert it to AWQ.
  2. if GPTQ model is quantized with --allow_mix_bits option, you can't convert it to AWQ.
  3. if GPTQ model is quantized with --act_order option, you can't convert it to AWQ.

Convert to onnx model

use --export_onnx ./onnx_model to export and save onnx model

python -m qllm --model  meta-llama/Llama-2-7b-chat-hf  --method=gptq  --dataset=pileval --nsamples=16  --save ./Llama-2-7b-chat-hf_awq_q4/ --export_onnx ./Llama-2-7b-chat-hf_awq_q4_onnx/

or you can convert a existing model in HF Hub

python -m qllm --load TheBloke/Llama-2-7B-Chat-AWQ --export_onnx=./onnx
python -m qllm --load TheBloke/Llama-2-7B-Chat-GPTQ --export_onnx=./onnx

model inference with the saved model

python -m qllm --load ./Llama-2-7b-4bit --eval

model inference with ORT

you may want to use genai to do generation with ORT.

import onnxruntime
from transformers import AutoTokenizer
onnx_path_str = './Llama-2-7b-4bit-onnx'

tokenizer = AutoTokenizer.from_pretrained(onnx_path_str, use_fast=True)
sample_inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
onnx_model_path = onnx_path_str+'/decoder_merged.onnx'
session = onnxruntime.InferenceSession(onnx_model_path, providers=['CUDAExecutionProvider'])
mask = np.ones(sample_inputs[0].shape, dtype=np.int64) if sample_inputs[1] is None else sample_inputs[1].cpu().numpy()
num_layers = model.config.num_hidden_layers
inputs = {'input_ids': sample_inputs[0].cpu().numpy(), 
          'attention_mask': mask, 
          'position_ids': np.arrange(0,sample_inputs[0], dtype=np.int64),
          'use_cache_branch': np.array([0], dtype=np.bool_)}
for i in range(num_layers):
    inputs[f'past_key_values.{i}.key'] = np.zeros((1, 32, 32, 128), dtype=np.float16)
    inputs[f'past_key_values.{i}.value'] = np.zeros((1, 32, 32, 128), dtype=np.float16)
outputs = session(None, inputs)

Load quantized model from hugingface/transformers

python -m qllm --load TheBloke/Llama-2-7B-Chat-AWQ --eval
python -m qllm --load TheBloke/Llama-2-7B-Chat-GPTQ --eval
python -m qllm --load TheBloke/Mixtral-8x7B-v0.1-GPTQ  --use_plugin

start a chatbot

you may need to install fschat and accelerate with pip

pip install fschat accelerate

use --use_plugin to enable a chatbot plugin

python -m qllm --model  meta-llama/Llama-2-7b-chat-hf  --method=awq  --dataset=pileval --nsamples=16  --use_plugin --save ./Llama-2-7b-chat-hf_awq_q4/

or 
python -m qllm --model  meta-llama/Llama-2-7b-chat-hf  --method=gptq  --dataset=pileval --nsamples=16  --use_plugin --save ./Llama-2-7b-chat-hf_gptq_q4/

For some users has transformers connect issues.

Please set environment with PROXY_PORT=your http proxy port

PowerShell $env:PROXY_PORT=1080

Bash export PROXY_PORT=1080

windows cmd set PROXY_PORT=1080

Acknowledgements

GPTQ

GPTQ-triton

AutoGPTQ

llm-awq

AutoAWQ.

HQQ

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

qllm-0.1.7.1-cp311-cp311-win_amd64.whl (568.8 kB view hashes)

Uploaded CPython 3.11 Windows x86-64

qllm-0.1.7.1-cp311-cp311-manylinux2014_x86_64.whl (542.7 kB view hashes)

Uploaded CPython 3.11

qllm-0.1.7.1-cp310-cp310-win_amd64.whl (566.6 kB view hashes)

Uploaded CPython 3.10 Windows x86-64

qllm-0.1.7.1-cp310-cp310-manylinux2014_x86_64.whl (541.3 kB view hashes)

Uploaded CPython 3.10

qllm-0.1.7.1-cp39-cp39-win_amd64.whl (565.9 kB view hashes)

Uploaded CPython 3.9 Windows x86-64

qllm-0.1.7.1-cp39-cp39-manylinux2014_x86_64.whl (541.4 kB view hashes)

Uploaded CPython 3.9

qllm-0.1.7.1-cp38-cp38-win_amd64.whl (566.4 kB view hashes)

Uploaded CPython 3.8 Windows x86-64

qllm-0.1.7.1-cp38-cp38-manylinux2014_x86_64.whl (541.1 kB view hashes)

Uploaded CPython 3.8

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page