A highly optimized LLM inference acceleration engine for Llama and its variants.

A Fast TTS Engine

My learning notes/codes for ML SYS.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

PearAI: Open Source AI Code Editor (Fork of VSCode). The PearAI Submodule (https://github.com/trypear/pearai-submodule) is a fork of Continue.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

Composable building blocks to build Llama Apps

An open-source RAG-based tool for chatting with your documents.

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

A package for parsing PDFs and analyzing their content using LLMs.

Microsoft's GraphRAG + AutoGen + Ollama + Chainlit = Fully Local & Free Multi-Agent RAG Superbot

SearchGPT / Perplexity clone, but personalised for you.

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

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

Agentic components of the Llama Stack APIs

SGLang is a fast serving framework for large language models and vision language models.

SearchGPT / Perplexity Pages clone, but personalised for you.

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

FlashInfer: Kernel Library for LLM Serving

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

TLLM_QMM strips the implementation of quantized kernels of Nvidia's TensorRT-LLM, removing NVInfer dependency and exposes ease of use Pytorch module. We modified the dequantation and weight preproc…

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

GPTModels - a multi model, window based LLM AI plugin for neovim, with an emphasis on stability and clean code

Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.