A high-throughput and memory-efficient inference and serving engine for LLMs

GroqFlow provides an automated tool flow for compiling machine learning and linear algebra workloads into Groq programs and executing those programs on GroqChip™ processors.

Train Models Contrastively in Pytorch

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

OpenAI compatible API for TensorRT LLM triton backend

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Espressif Audio Development Framework

4 bits quantization of LLaMa using GPTQ

An unofficial PyTorch implementation of the audio LM VALL-E

The ESP-BOX is a new generation AIoT development platform released by Espressif Systems.

Instruct-tune LLaMA on consumer hardware

The Triton Model Navigator is a tool that provides the ability to automate the process of model deployment on the Triton Inference Server.

Experiments with Model Training, Deployment & Monitoring

HTTP 1.x proxy that makes old web browsers usable again in the Web 2.0 world.

WebOne HTTP1.X Proxy

Audio fingerprinting and recognition in Python

Docker container to run rtlsdir-airband + ice cast to stream ATC audio locally or to a remote server

Multichannel AM/NFM demodulator

Mirror of git://source.ffmpeg.org/ffmpeg.git

FFmpeg for browser and node, powered by WebAssembly

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, Korean, Chinese and Easy to adapt for other languages)

Shell script to set up a Raspberry Pi/Odroid/PC with RetroArch emulator and various cores

NeMo: a toolkit for conversational AI

A TensorFlow implementation of Baidu's DeepSpeech architecture

This is the official location of the Kaldi project.

This sample shows how to train and deploy a deep learning model for the real time redaction of faces from video streams using the NVIDIA DeepStream SDK

Fast and accurate object detection with end-to-end GPU optimization