-
M.I.A Robotics
- Alexandria, Egypt
- https://islam231bi.github.io/
- @Pointer23_
Highlights
- Pro
Stars
An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine
FlashInfer: Kernel Library for LLM Serving
A web tool to explore the ASTs generated by various parsers.
FastAPI framework, high performance, easy to learn, fast to code, ready for production
A benchmark framework for LLM serving performance, based on API call
Fast and memory-efficient exact attention
dstack is an open-source alternative to Kubernetes, designed to simplify development, training, and deployment of AI across any cloud or on-prem. It supports NVIDIA, AMD, and TPU.
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Code at the speed of thought β Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
A Decentralized Operating System for ZK Applications
Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
A modular graph-based Retrieval-Augmented Generation (RAG) system
Python composable command line interface toolkit
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Simplifying reinforcement learning for complex game environments
π©πΏβπ»π¨πΎβπ»π©πΌβπ»π¨π½βπ»π©π»βπ» Awesome Developers, Streaming
Projects for an undergraduate OS course
List of Computer Science courses with video lectures.
Robust Speech Recognition via Large-Scale Weak Supervision
A deep-dive on the entire history of deep-learning