Best AI tools for< Quantize Checkpoints >

The NVIDIA TensorRT Model Optimizer is a library designed to quantize and compress deep learning models for optimized inference on GPUs. It offers state-of-the-art model optimization techniques including quantization and sparsity to reduce inference costs for generative AI models. Users can easily stack different optimization techniques to produce quantized checkpoints from torch or ONNX models. The quantized checkpoints are ready for deployment in inference frameworks like TensorRT-LLM or TensorRT, with planned integrations for NVIDIA NeMo and Megatron-LM. The tool also supports 8-bit quantization with Stable Diffusion for enterprise users on NVIDIA NIM. Model Optimizer is available for free on NVIDIA PyPI, and this repository serves as a platform for sharing examples, GPU-optimized recipes, and collecting community feedback.

ChatLLM.cpp is a pure C++ implementation tool for real-time chatting with RAG on your computer. It supports inference of various models ranging from less than 1B to more than 300B. The tool provides accelerated memory-efficient CPU inference with quantization, optimized KV cache, and parallel computing. It allows streaming generation with a typewriter effect and continuous chatting with virtually unlimited content length. ChatLLM.cpp also offers features like Retrieval Augmented Generation (RAG), LoRA, Python/JavaScript/C bindings, web demo, and more possibilities. Users can clone the repository, quantize models, build the project using make or CMake, and run quantized models for interactive chatting.

LLaMa2lang is a repository containing convenience scripts to finetune LLaMa3-8B (or any other foundation model) for chat towards any language that isn't English. The repository aims to improve the performance of LLaMa3 for non-English languages by combining fine-tuning with RAG. Users can translate datasets, extract threads, turn threads into prompts, and finetune models using QLoRA and PEFT. Additionally, the repository supports translation models like OPUS, M2M, MADLAD, and base datasets like OASST1 and OASST2. The process involves loading datasets, translating them, combining checkpoints, and running inference using the newly trained model. The repository also provides benchmarking scripts to choose the right translation model for a target language.

QServe is a serving system designed for efficient and accurate Large Language Models (LLM) on GPUs with W4A8KV4 quantization. It achieves higher throughput compared to leading industry solutions, allowing users to achieve A100-level throughput on cheaper L40S GPUs. The system introduces the QoQ quantization algorithm with 4-bit weight, 8-bit activation, and 4-bit KV cache, addressing runtime overhead challenges. QServe improves serving throughput for various LLM models by implementing compute-aware weight reordering, register-level parallelism, and fused attention memory-bound techniques.

Awesome LLM compression research papers and tools to accelerate LLM training and inference.

rwkv.cpp is a port of BlinkDL/RWKV-LM to ggerganov/ggml, supporting FP32, FP16, and quantized INT4, INT5, and INT8 inference. It focuses on CPU but also supports cuBLAS. The project provides a C library rwkv.h and a Python wrapper. RWKV is a large language model architecture with models like RWKV v5 and v6. It requires only state from the previous step for calculations, making it CPU-friendly on large context lengths. Users are advised to test all available formats for perplexity and latency on a representative dataset before serious use.

LitGPT is a command-line tool designed to easily finetune, pretrain, evaluate, and deploy 20+ LLMs **on your own data**. It features highly-optimized training recipes for the world's most powerful open-source large-language-models (LLMs).

llm-compressor is an easy-to-use library for optimizing models for deployment with vllm. It provides a comprehensive set of quantization algorithms, seamless integration with Hugging Face models and repositories, and supports mixed precision, activation quantization, and sparsity. Supported algorithms include PTQ, GPTQ, SmoothQuant, and SparseGPT. Installation can be done via git clone and local pip install. Compression can be easily applied by selecting an algorithm and calling the oneshot API. The library also offers end-to-end examples for model compression. Contributions to the code, examples, integrations, and documentation are appreciated.

Torchtune is a PyTorch-native library for easily authoring, fine-tuning, and experimenting with LLMs. It provides native-PyTorch implementations of popular LLMs using composable and modular building blocks, easy-to-use and hackable training recipes for popular fine-tuning techniques, YAML configs for easily configuring training, evaluation, quantization, or inference recipes, and built-in support for many popular dataset formats and prompt templates to help you quickly get started with training.

Bark.cpp is a C/C++ implementation of the Bark model, a real-time, multilingual text-to-speech generation model. It supports AVX, AVX2, and AVX512 for x86 architectures, and is compatible with both CPU and GPU backends. Bark.cpp also supports mixed F16/F32 precision and 4-bit, 5-bit, and 8-bit integer quantization. It can be used to generate realistic-sounding audio from text prompts.

This repository contains convenience scripts to finetune LLaMa3-8B (or any other foundation model) for chat towards any language (that isn't English). The rationale behind this is that LLaMa3 is trained on primarily English data and while it works to some extent for other languages, its performance is poor compared to English.

Awesome-LLM-Inference: A curated list of 📙Awesome LLM Inference Papers with Codes, check 📖Contents for more details. This repo is still updated frequently ~ 👨‍💻‍ Welcome to star ⭐️ or submit a PR to this repo!

ChatGLM.cpp is a C++ implementation of ChatGLM-6B, ChatGLM2-6B, ChatGLM3-6B and more LLMs for real-time chatting on your MacBook. It is based on ggml, working in the same way as llama.cpp. ChatGLM.cpp features accelerated memory-efficient CPU inference with int4/int8 quantization, optimized KV cache and parallel computing. It also supports P-Tuning v2 and LoRA finetuned models, streaming generation with typewriter effect, Python binding, web demo, api servers and more possibilities.

The AI Toolkit by Ostris is a collection of tools for machine learning, specifically designed for image generation, LoRA (latent representations of attributes) extraction and manipulation, and model training. It provides a user-friendly interface and extensive documentation to make it accessible to both developers and non-developers. The toolkit is actively under development, with new features and improvements being added regularly. Some of the key features of the AI Toolkit include: - Batch Image Generation: Allows users to generate a batch of images based on prompts or text files, using a configuration file to specify the desired settings. - LoRA (lierla), LoCON (LyCORIS) Extractor: Facilitates the extraction of LoRA and LoCON representations from pre-trained models, enabling users to modify and manipulate these representations for various purposes. - LoRA Rescale: Provides a tool to rescale LoRA weights, allowing users to adjust the influence of specific attributes in the generated images. - LoRA Slider Trainer: Enables the training of LoRA sliders, which can be used to control and adjust specific attributes in the generated images, offering a powerful tool for fine-tuning and customization. - Extensions: Supports the creation and sharing of custom extensions, allowing users to extend the functionality of the toolkit with their own tools and scripts. - VAE (Variational Auto Encoder) Trainer: Facilitates the training of VAEs for image generation, providing users with a tool to explore and improve the quality of generated images. The AI Toolkit is a valuable resource for anyone interested in exploring and utilizing machine learning for image generation and manipulation. Its user-friendly interface, extensive documentation, and active development make it an accessible and powerful tool for both beginners and experienced users.

Qwen is a series of large language models developed by Alibaba DAMO Academy. It outperforms the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen models outperform the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen-72B achieves better performance than LLaMA2-70B on all tasks and outperforms GPT-3.5 on 7 out of 10 tasks.

This repository provides a systematic and comprehensive review of efficient LLMs research. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient LLMs topics from **model-centric** , **data-centric** , and **framework-centric** perspective, respectively. We hope our survey and this GitHub repository can serve as valuable resources to help researchers and practitioners gain a systematic understanding of the research developments in efficient LLMs and inspire them to contribute to this important and exciting field.

The stable-diffusion.cpp repository provides an implementation for inferring stable diffusion in pure C/C++. It offers features such as support for different versions of stable diffusion, lightweight and dependency-free implementation, various quantization support, memory-efficient CPU inference, GPU acceleration, and more. Users can download the built executable program or build it manually. The repository also includes instructions for downloading weights, building from scratch, using different acceleration methods, running the tool, converting weights, and utilizing various features like Flash Attention, ESRGAN upscaling, PhotoMaker support, and more. Additionally, it mentions future TODOs and provides information on memory requirements, bindings, UIs, contributors, and references.

qlora-pipe is a pipeline parallel training script designed for efficiently training large language models that cannot fit on one GPU. It supports QLoRA, LoRA, and full fine-tuning, with efficient model loading and the ability to load any dataset that Axolotl can handle. The script allows for raw text training, resuming training from a checkpoint, logging metrics to Tensorboard, specifying a separate evaluation dataset, training on multiple datasets simultaneously, and supports various models like Llama, Mistral, Mixtral, Qwen-1.5, and Cohere (Command R). It handles pipeline- and data-parallelism using Deepspeed, enabling users to set the number of GPUs, pipeline stages, and gradient accumulation steps for optimal utilization.