qzhong0605

ChatLearn

cupy

NumPy & SciPy for GPU

schedule

Python job scheduling for humans.

semikong

First Open-Source Industry-Specific Model for Semiconductors

yappi

Yet Another Python Profiler, but this time multithreading, asyncio and gevent aware.

OpenHands

🙌 OpenHands: Code Less, Make More

mojo

The Mojo Programming Language

lerobot

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

superfile

Pretty fancy and modern terminal file manager

mscclpp

MSCCL++: A GPU-driven communication stack for scalable AI applications

nccl

Optimized primitives for collective multi-GPU communication

self-operating-computer

A framework to enable multimodal models to operate a computer.

watchdog

Python library and shell utilities to monitor filesystem events.

OS-Copilot

An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.

ollama

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

pipx

Install and Run Python Applications in Isolated Environments

Qwen2.5

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Sequoia

scalable and robust tree-based speculative decoding algorithm

sccache

Sccache is a ccache-like tool. It is used as a compiler wrapper and avoids compilation when possible. Sccache has the capability to utilize caching in remote storage environments, including various cloud storage options, or alternatively, in local storage.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

grok-1

Grok open release

FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving

GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

stats

macOS system monitor in your menu bar

vimspector

vimspector - A multi-language debugging system for Vim

autogen

A programming framework for agentic AI 🤖

loguru

Python logging made (stupidly) simple

excalidraw

Virtual whiteboard for sketching hand-drawn like diagrams

TransformerCompression

For releasing code related to compression methods for transformers, accompanying our publications