Board Archive Editions Search Newsletter

01BoardToday on GitHub
02ArchiveEvery day we kept
03EditionsThe Weekly Star
04SearchThe whole record
05NewsletterEvery Monday

How we pick PrivacyCaptured daily

A field guide to open source.
Follow the work. Keep the record.

How we pick Privacy

A project by Patrick Xin

Board Archive Editions Search Newsletter

01BoardToday on GitHub
02ArchiveEvery day we kept
03EditionsThe Weekly Star
04SearchThe whole record
05NewsletterEvery Monday

How we pick PrivacyCaptured daily

microsoft/BitNet — Starlogs

microsoft /

BitNet

An official inference framework for running 1-bit (1.58-bit) LLMs efficiently on CPU and GPU.

framework
local-llm

Stars: 40,842
Sightings: 1
Best rank: No. 8
First seen: Oct 12
Language: C++

Open on GitHub ↗

Each star is a day on a trending board. The higher it ranked that day, the larger and higher the star.

First seen Oct 12, No. 8, its highest

What it's for.

Run 1-bit LLM inference
Run quantized models on CPU or GPU
Chat with instruct BitNet models

How you start.

Clone the repository recursively and install dependencies
Set up the environment and download/quantize a model
Run inference with a prompt, optionally in chat mode

Before you begin.

Requires python>=3.10, cmake>=3.22, clang>=18; conda is highly recommended.
Windows users must install Visual Studio 2022 with C++ and clang toolset options.

Stars

The chart appears once we have counts from two days.

Sightings1 days on the boards

no boards keptnot on a boardfewer starsmore

Nearby

Close by description, tags or language

modular
modular
Open-source components of the Modular Platform: the Mojo language and the MAX framework for AI development and deployment.

nodejs

node

Open-source, cross-platform JavaScript runtime environment, governed openly with support from the OpenJS Foundation.

longbridge

gpui-kit

A Rust framework for building high-performance desktop applications on GPUI, offering styled components, layout, and editing primitives.