https://github.com/microsoft/BitNet
Official inference framework for 1-bit LLMs
https://github.com/microsoft/BitNet
Last synced: 3 months ago
JSON representation
Official inference framework for 1-bit LLMs
- Host: GitHub
- URL: https://github.com/microsoft/BitNet
- Owner: microsoft
- License: mit
- Created: 2024-08-05T09:07:38.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-02-18T13:13:36.000Z (3 months ago)
- Last Synced: 2025-03-02T10:01:50.887Z (3 months ago)
- Language: C++
- Homepage:
- Size: 1.93 MB
- Stars: 12,772
- Watchers: 133
- Forks: 898
- Open Issues: 74
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
Awesome Lists containing this project
- awesome-generative-ai - bitnet.cpp - Official inference framework for 1-bit LLMs, by Microsoft. [#opensource](https://github.com/microsoft/BitNet) (Coding / Developer tools)
- StarryDivineSky - microsoft/BitNet - 7 个令牌），从而显着增强在本地设备上运行LLMs的潜力。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
- AiTreasureBox - microsoft/BitNet - 05-13_18771_138](https://img.shields.io/github/stars/microsoft/BitNet.svg)|Official inference framework for 1-bit LLMs| (Repos)
- awesome - microsoft/BitNet - Official inference framework for 1-bit LLMs (C++)
README
# bitnet.cpp
[](https://opensource.org/licenses/MIT)
bitnet.cpp is the official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support **fast** and **lossless** inference of 1.58-bit models on CPU (with NPU and GPU support coming next).
The first release of bitnet.cpp is to support inference on CPUs. bitnet.cpp achieves speedups of **1.37x** to **5.07x** on ARM CPUs, with larger models experiencing greater performance gains. Additionally, it reduces energy consumption by **55.4%** to **70.0%**, further boosting overall efficiency. On x86 CPUs, speedups range from **2.37x** to **6.17x** with energy reductions between **71.9%** to **82.2%**. Furthermore, bitnet.cpp can run a 100B BitNet b1.58 model on a single CPU, achieving speeds comparable to human reading (5-7 tokens per second), significantly enhancing the potential for running LLMs on local devices. Please refer to the [technical report](https://arxiv.org/abs/2410.16144) for more details.
>The tested models are dummy setups used in a research context to demonstrate the inference performance of bitnet.cpp.
## Demo
A demo of bitnet.cpp running a BitNet b1.58 3B model on Apple M2:
https://github.com/user-attachments/assets/7f46b736-edec-4828-b809-4be780a3e5b1
## What's New:
- 02/18/2025 [Bitnet.cpp: Efficient Edge Inference for Ternary LLMs](https://arxiv.org/abs/2502.11880) 
- 11/08/2024 [BitNet a4.8: 4-bit Activations for 1-bit LLMs](https://arxiv.org/abs/2411.04965)
- 10/21/2024 [1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs](https://arxiv.org/abs/2410.16144)
- 10/17/2024 bitnet.cpp 1.0 released.
- 03/21/2024 [The-Era-of-1-bit-LLMs__Training_Tips_Code_FAQ](https://github.com/microsoft/unilm/blob/master/bitnet/The-Era-of-1-bit-LLMs__Training_Tips_Code_FAQ.pdf)
- 02/27/2024 [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://arxiv.org/abs/2402.17764)
- 10/17/2023 [BitNet: Scaling 1-bit Transformers for Large Language Models](https://arxiv.org/abs/2310.11453)
## Acknowledgements
This project is based on the [llama.cpp](https://github.com/ggerganov/llama.cpp) framework. We would like to thank all the authors for their contributions to the open-source community. Also, bitnet.cpp's kernels are built on top of the Lookup Table methodologies pioneered in [T-MAC](https://github.com/microsoft/T-MAC/). For inference of general low-bit LLMs beyond ternary models, we recommend using T-MAC.
## Supported Models
❗️**We use existing 1-bit LLMs available on [Hugging Face](https://huggingface.co/) to demonstrate the inference capabilities of bitnet.cpp. These models are neither trained nor released by Microsoft. We hope the release of bitnet.cpp will inspire the development of 1-bit LLMs in large-scale settings in terms of model size and training tokens.**
Model
Parameters
CPU
Kernel
I2_S
TL1
TL2
bitnet_b1_58-large
0.7B
x86
✅
❌
✅
ARM
✅
✅
❌
bitnet_b1_58-3B
3.3B
x86
❌
❌
✅
ARM
❌
✅
❌
Llama3-8B-1.58-100B-tokens
8.0B
x86
✅
❌
✅
ARM
✅
✅
❌
Falcon3 Family
1B-10B
x86
✅
❌
✅
ARM
✅
✅
❌
## Installation
### Requirements
- python>=3.9
- cmake>=3.22
- clang>=18
- For Windows users, install [Visual Studio 2022](https://visualstudio.microsoft.com/downloads/). In the installer, toggle on at least the following options(this also automatically installs the required additional tools like CMake):
- Desktop-development with C++
- C++-CMake Tools for Windows
- Git for Windows
- C++-Clang Compiler for Windows
- MS-Build Support for LLVM-Toolset (clang)
- For Debian/Ubuntu users, you can download with [Automatic installation script](https://apt.llvm.org/)
`bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)"`
- conda (highly recommend)
### Build from source
> [!IMPORTANT]
> If you are using Windows, please remember to always use a Developer Command Prompt / PowerShell for VS2022 for the following commands
1. Clone the repo
```bash
git clone --recursive https://github.com/microsoft/BitNet.git
cd BitNet
```
2. Install the dependencies
```bash
# (Recommended) Create a new conda environment
conda create -n bitnet-cpp python=3.9
conda activate bitnet-cpp
pip install -r requirements.txt
```
3. Build the project
```bash
# Download the model from Hugging Face, convert it to quantized gguf format, and build the project
python setup_env.py --hf-repo tiiuae/Falcon3-7B-Instruct-1.58bit -q i2_s
# Or you can manually download the model and run with local path
huggingface-cli download tiiuae/Falcon3-7B-Instruct-1.58bit --local-dir models/Falcon3-7B-Instruct-1.58bit
python setup_env.py -md models/Falcon3-7B-Instruct-1.58bit -q i2_s
```
usage: setup_env.py [-h] [--hf-repo {1bitLLM/bitnet_b1_58-large,1bitLLM/bitnet_b1_58-3B,HF1BitLLM/Llama3-8B-1.58-100B-tokens,tiiuae/Falcon3-1B-Instruct-1.58bit,tiiuae/Falcon3-3B-Instruct-1.58bit,tiiuae/Falcon3-7B-Instruct-1.58bit,tiiuae/Falcon3-10B-Instruct-1.58bit}] [--model-dir MODEL_DIR] [--log-dir LOG_DIR] [--quant-type {i2_s,tl1}] [--quant-embd]
[--use-pretuned]
Setup the environment for running inference
optional arguments:
-h, --help show this help message and exit
--hf-repo {1bitLLM/bitnet_b1_58-large,1bitLLM/bitnet_b1_58-3B,HF1BitLLM/Llama3-8B-1.58-100B-tokens,tiiuae/Falcon3-1B-Instruct-1.58bit,tiiuae/Falcon3-3B-Instruct-1.58bit,tiiuae/Falcon3-7B-Instruct-1.58bit,tiiuae/Falcon3-10B-Instruct-1.58bit}, -hr {1bitLLM/bitnet_b1_58-large,1bitLLM/bitnet_b1_58-3B,HF1BitLLM/Llama3-8B-1.58-100B-tokens,tiiuae/Falcon3-1B-Instruct-1.58bit,tiiuae/Falcon3-3B-Instruct-1.58bit,tiiuae/Falcon3-7B-Instruct-1.58bit,tiiuae/Falcon3-10B-Instruct-1.58bit}
Model used for inference
--model-dir MODEL_DIR, -md MODEL_DIR
Directory to save/load the model
--log-dir LOG_DIR, -ld LOG_DIR
Directory to save the logging info
--quant-type {i2_s,tl1}, -q {i2_s,tl1}
Quantization type
--quant-embd Quantize the embeddings to f16
--use-pretuned, -p Use the pretuned kernel parameters
## Usage
### Basic usage
```bash
# Run inference with the quantized model
python run_inference.py -m models/Falcon3-7B-Instruct-1.58bit/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
```
usage: run_inference.py [-h] [-m MODEL] [-n N_PREDICT] -p PROMPT [-t THREADS] [-c CTX_SIZE] [-temp TEMPERATURE] [-cnv]
Run inference
optional arguments:
-h, --help show this help message and exit
-m MODEL, --model MODEL
Path to model file
-n N_PREDICT, --n-predict N_PREDICT
Number of tokens to predict when generating text
-p PROMPT, --prompt PROMPT
Prompt to generate text from
-t THREADS, --threads THREADS
Number of threads to use
-c CTX_SIZE, --ctx-size CTX_SIZE
Size of the prompt context
-temp TEMPERATURE, --temperature TEMPERATURE
Temperature, a hyperparameter that controls the randomness of the generated text
-cnv, --conversation Whether to enable chat mode or not (for instruct models.)
(When this option is turned on, the prompt specified by -p will be used as the system prompt.)
### Benchmark
We provide scripts to run the inference benchmark providing a model.
```
usage: e2e_benchmark.py -m MODEL [-n N_TOKEN] [-p N_PROMPT] [-t THREADS]
Setup the environment for running the inference
required arguments:
-m MODEL, --model MODEL
Path to the model file.
optional arguments:
-h, --help
Show this help message and exit.
-n N_TOKEN, --n-token N_TOKEN
Number of generated tokens.
-p N_PROMPT, --n-prompt N_PROMPT
Prompt to generate text from.
-t THREADS, --threads THREADS
Number of threads to use.
```
Here's a brief explanation of each argument:
- `-m`, `--model`: The path to the model file. This is a required argument that must be provided when running the script.
- `-n`, `--n-token`: The number of tokens to generate during the inference. It is an optional argument with a default value of 128.
- `-p`, `--n-prompt`: The number of prompt tokens to use for generating text. This is an optional argument with a default value of 512.
- `-t`, `--threads`: The number of threads to use for running the inference. It is an optional argument with a default value of 2.
- `-h`, `--help`: Show the help message and exit. Use this argument to display usage information.
For example:
```sh
python utils/e2e_benchmark.py -m /path/to/model -n 200 -p 256 -t 4
```
This command would run the inference benchmark using the model located at `/path/to/model`, generating 200 tokens from a 256 token prompt, utilizing 4 threads.
For the model layout that do not supported by any public model, we provide scripts to generate a dummy model with the given model layout, and run the benchmark on your machine:
```bash
python utils/generate-dummy-bitnet-model.py models/bitnet_b1_58-large --outfile models/dummy-bitnet-125m.tl1.gguf --outtype tl1 --model-size 125M
# Run benchmark with the generated model, use -m to specify the model path, -p to specify the prompt processed, -n to specify the number of token to generate
python utils/e2e_benchmark.py -m models/dummy-bitnet-125m.tl1.gguf -p 512 -n 128
```