lee/BitNet
1
0
Fork 0
mirror of https://github.com/microsoft/BitNet.git synced 2026-05-03 11:20:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #276 from microsoft/readme-dev

Browse Source 
refine readme for gpu kernel
This commit is contained in:
tsong-ms
2025-05-20 16:14:18 +08:00
committed by GitHub
parent 6c2c08f67e 6197e9feb0
commit 70285e0154
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -3
View File
@@ -4,9 +4,9 @@
[<img src="./assets/header_model_release.png" alt="BitNet Model on Hugging Face" width="800"/>](https://huggingface.co/microsoft/BitNet-b1.58-2B-4T)
Try it out via this [demo](https://bitnet-demo.azurewebsites.net/), or [build and run](https://github.com/microsoft/BitNet?tab=readme-ov-file#build-from-source) it on your own CPU.
Try it out via this [demo](https://bitnet-demo.azurewebsites.net/), or build and run it on your own [CPU](https://github.com/microsoft/BitNet?tab=readme-ov-file#build-from-source) or [GPU](https://github.com/microsoft/BitNet/blob/main/gpu/README.md).
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).
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 and GPU (NPU support will 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.
@@ -22,7 +22,8 @@ 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:
- 04/14/2025 [BitNet Official 2B Parameter Model on Hugging Face](https://huggingface.co/microsoft/BitNet-b1.58-2B-4T) ![NEW](https://img.shields.io/badge/NEW-red)
- 05/20/2025 [BitNet Official GPU inference kernel](https://github.com/microsoft/BitNet/blob/main/gpu/README.md) ![NEW](https://img.shields.io/badge/NEW-red)
- 04/14/2025 [BitNet Official 2B Parameter Model on Hugging Face](https://huggingface.co/microsoft/BitNet-b1.58-2B-4T)
- 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)