Loading...
Loading...
Browse all stories on DeepNewz
VisitWhat will be the primary use case for BitNet b1.58 by end of 2024?
Consumer devices • 25%
Enterprise solutions • 25%
Research and academia • 25%
Other • 25%
Industry reports and user case studies
Microsoft Open-Sources BitNet Framework for 1-Bit LLMs Including BitNet b1.58
Oct 20, 2024, 01:37 AM
Microsoft has open-sourced bitnet.cpp, the official inference framework for 1-bit large language models (LLMs), such as BitNet b1.58 and BitNet Llama8B. This framework offers a suite of optimized kernels that support fast and lossless inference of 1.58-bit models on CPUs, with NPU and GPU support expected in the future. BitNet technology significantly speeds up the calculation of large-scale language models, which previously required 4 or more bits of information. This development allows 100 billion parameter models to run on local devices, quantized with BitNet b1.58, at a rate of 5-7 tokens per second using a single CPU. Exo had previously open-sourced the first ternary model implementation for Apple Silicon in March, and now BitNet b1.58 can run on Apple M2 CPUs.
View original story
Decentralized Finance (DeFi) • 25%
Non-Fungible Tokens (NFTs) • 25%
Supply Chain Management • 25%
Other • 25%
Consumer Electronics • 25%
Enterprise Software • 25%
Automotive • 25%
Healthcare • 25%
Store of value • 25%
Speculative investment • 25%
Medium of exchange • 25%
Other • 25%
DeFi • 25%
NFTs • 25%
Gaming • 25%
Other • 25%
Payments • 25%
DeFi • 25%
Gaming • 25%
Other • 25%
Identity and reputation-based consumer network • 25%
Decentralized finance (DeFi) • 25%
Gaming and NFTs • 25%
Other • 25%
DeFi lending/borrowing • 25%
Decentralized exchanges • 25%
Yield farming • 25%
Other • 25%
Speculative Investment • 25%
Store of Value • 25%
Payment Method • 25%
Other • 25%
Digital commerce • 25%
Social media interaction • 25%
Crypto trading • 25%
Other • 25%
Gaming • 25%
Financial Services • 25%
Supply Chain Management • 25%
Other • 25%
Cross-chain liquidity coordination • 25%
Rebalancing costs reduction • 25%
Scalable Chain Abstraction • 25%
Other • 25%
Cross-chain Transactions • 25%
MEV Internalization • 25%
Fast DeFi Transactions • 25%
Other • 25%
Remains stable • 25%
Decreases • 25%
Increases significantly • 25%
Increases slightly • 25%