- Serbia, Leskovac
- https://markotasic.com
- @mtasic85
Stars
Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.
Modern and easy to use SQL client for MySQL, Postgres, SQLite, SQL Server, and more. Linux, MacOS, and Windows.
A modern, user friendly, generic, type-safe and fast C99 container library: String, Vector, Sorted and Unordered Map and Set, Deque, Forward List, Smart Pointers, Bitset and Random numbers.
Reliable model swapping for any local OpenAI compatible server - llama.cpp, vllm, etc
A webshell and a normal file that have the same MD5
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
A library for mechanistic interpretability of GPT-style language models
A concise, beginner-friendly introduction to the core ideas of linear algebra.
[ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2
Stream video torrents in your web browser with ease.
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.
A distributed key value store in under 1000 lines. Used in production at comma.ai
a concurrent hash array mapped trie implementation in go
Parse, Resolve, and Dereference JSON Schema $ref pointers in Node and browsers
🦛 CHONK docs with Chonkie ✨ — The no-nonsense RAG library
Prompts for our Grok chat assistant and the `@grok` bot on X.
Distributed SQL database in Rust, written as an educational project
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Rich is a Python library for rich text and beautiful formatting in the terminal.
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
From the Transistor to the Web Browser, a rough outline for a 12 week course
DFloat11: Lossless LLM Compression for Efficient GPU Inference



