minhopark-neubla

professional-programming

A collection of learning resources for curious software engineers

llm.c

LLM training in simple, raw C/CUDA

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

mlc-llm

Universal LLM Deployment Engine with ML Compilation

codellama

Inference code for CodeLlama models

ML-YouTube-Courses

📺 Discover the latest machine learning / AI courses on YouTube.

chroma

the AI-native open-source embedding database

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

scalene

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

gorilla

Gorilla: An API store for LLMs

magika

Detect file content types with deep learning

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

OLMo

Modeling, training, eval, and inference code for OLMo

Machine-Learning-Interviews

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

cppinsights

C++ Insights - See your source code with the eyes of a compiler

torchtune

A Native-PyTorch Library for LLM Fine-tuning

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

ai-tech-interview

👩‍💻👨‍💻 AI 엔지니어 기술 면접 스터디 (⭐️ 1k+)

openllmetry

Open-source observability for your LLM application, based on OpenTelemetry

nanotron

Minimalistic large language model 3D-parallelism training

Triton-Puzzles

Puzzles for learning Triton

chronon

Chronon is a data platform for serving for AI/ML applications.

intel-npu-acceleration-library

Intel® NPU Acceleration Library

contoso-chat

This sample has the full End2End process of creating RAG application with Prompt Flow and AI Studio. It includes GPT 3.5 Turbo LLM application code, evaluations, deployment automation with AZD CLI, GitHub actions for evaluation and deployment and intent mapping for multiple LLM task mapping.

effective_pandas_book

Errata and code for Effective Pandas book

gpu-optimization-workshop

Slides, notes, and materials for the workshop

KVQuant

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

metricx

QLLM

[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"