Beast code in Giters

Yigal Korman's starred repositories

ml-depth-pro

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Language:PythonNOASSERTION79600

zipnn

A Lossless Compression Library for AI pipelines

Language:PythonNOASSERTION13100

tensorizer

Module, Model, and Tensor Serialization/Deserialization

Language:PythonMIT18000

techmap

Israeli tech companies map

NOASSERTION6200

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.

Language:Jupyter NotebookNOASSERTION707900

tau

Open source distributed Platform as a Service (PaaS). A self-hosted Vercel / Netlify / Cloudflare alternative.

Language:GoBSD-3-Clause326100

chitchat

Cluster membership protocol with failure detection inspired by Cassandra and DynamoDB

Language:RustMIT26100

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonMIT1963700

OpenRA

Open Source real-time strategy game engine for early Westwood games such as Command & Conquer: Red Alert written in C# using SDL and OpenGL. Runs on Windows, Linux, *BSD and Mac OS X.

Language:C#GPL-3.01464600

llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

Language:Jupyter Notebook1201300

hebrew_whisper

Hebrew whisper powerful transcription and translation tool

Language:PythonMIT5000

LLocalSearch

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

Language:GoApache-2.0559700

llamafile

Distribute and run LLMs with a single file.

Language:C++NOASSERTION1949300

monolith

⬛️ CLI tool for saving complete web pages as a single HTML file

Language:RustCC0-1.01097600

highway

Performance-portable, length-agnostic SIMD with runtime dispatch

Language:C++Apache-2.0412800

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

Language:C++Apache-2.0593900

crucible

A storage service.

Language:RustMPL-2.016600

StableCascade

Official Code for Stable Cascade

Language:Jupyter NotebookMIT652700

orbit

C/C++ Performance Profiler

Language:C++BSD-2-Clause418100

knowhere

Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.

Language:C++Apache-2.017700

ps-lite

A lightweight parameter server interface

Language:C++Apache-2.0153400

scx

sched_ext schedulers and tools

Language:CGPL-2.084500

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

Apache-2.01646500

gitui

Blazing 💥 fast terminal-ui for git written in rust 🦀

Language:RustMIT1834200

tcpshm

A connection-oriented persistent message queue framework based on TCP or SHM(shared memory)

Language:C++MIT45500

qemu-user-static

:earth_africa: `/usr/bin/qemu-*-static`

Language:ShellMIT242400

skopeo

Work with remote images registries - retrieving information, images, signing content

Language:GoApache-2.0812000

IJCAI2023-OptimalShardedDataParallel

[IJCAI2023] An automated parallel training system that combines the advantages from both data and model parallelism. If you have any interests, please visit/star/fork https://github.com/Youhe-Jiang/OptimalShardedDataParallel

Language:PythonMIT5100

nsync

nsync is a C library that exports various synchronization primitives, such as mutexes

Language:CApache-2.093400

OpenSearch

🔎 Open source distributed and RESTful search engine.

Language:JavaApache-2.0962100

ykorman