Fast and Furious AMD Kernels

This package contains the original 2012 AlexNet code.

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

Optimizing inference proxy for LLMs

Best practices & guides on how to write distributed pytorch training code

Triton implementation of FlashAttention2 that adds Custom Masks.

[MalayMMLU] This is the first-ever Bahasa Melayu multitask benchmark designed to elevate the performance of Large Language Models (LLMs) and Large Vision Language Models (LVLMs).

List of Malay words in both Rumi and Jawi scripts

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

This is a Sarawak Malay speech and text data for the purpose of speech technology research. The data was collected by Faculty of Computer Science and Information Technology, Universiti Malaysia Sar…

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

WebLINX is a benchmark for building web navigation agents with conversational capabilities

A small automatic differentiation engine, supporting higher-order derivatives

A translation app for Bahasa Melayu to English with support for Manglish and bahasa pasar.

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

AI powered speech denoising and enhancement

HTTP/WebSocket proxy for starlette/FastAPI

Machine Learning Engineering Open Book

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

Fast inference engine for Transformer models

Fast & Simple repository for pre-training and fine-tuning T5-style models

A Data Streaming Library for Efficient Neural Network Training

LLM as a Chatbot Service

A family of diffusion models for text-to-audio generation.