Accessible large language models via k-bit quantization for PyTorch.

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

基于深度强化学习的开源自动因子工厂。

:house: My Home Assistant configuration, a bit different that others :) Be sure to :star2: this repository for updates!

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Secure boot for 32-bit Microcontrollers!

Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer.

A Blocks / JavaScript code editor for the micro:bit built on Microsoft MakeCode

Operate Fluent Bit and Fluentd in the Kubernetes way - Previously known as FluentBit Operator

Shenzhen MSU-BIT University PolarBear Team's Sentry Navigation Sim2Real Package for RoboMaster2025. QQ group: 932119307

LLM-powered trading agents that turn plain natural language into a five-pillar strategy: Trend, Mean-Reversion, Momentum, Volume, and Risk. Each strategy is hosted, self-evolving, configurable through 30+ tunable parameters, and bit-exact between backtest and live execution. Built for simulated Hyperliquid perpetuals.

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。