Best AI tools for< Quantize Inference >

BitBLAS is a library for mixed-precision BLAS operations on GPUs, for example, the $W_{wdtype}A_{adtype}$ mixed-precision matrix multiplication where $C_{cdtype}[M, N] = A_{adtype}[M, K] \times W_{wdtype}[N, K]$. BitBLAS aims to support efficient mixed-precision DNN model deployment, especially the $W_{wdtype}A_{adtype}$ quantization in large language models (LLMs), for example, the $W_{UINT4}A_{FP16}$ in GPTQ, the $W_{INT2}A_{FP16}$ in BitDistiller, the $W_{INT2}A_{INT8}$ in BitNet-b1.58. BitBLAS is based on techniques from our accepted submission at OSDI'24.

This repository provides support for inference RWKV models on Qualcomm HTP (Hexagon Tensor Processor) using QNN SDK. It supports RWKV v5, v6, and experimentally v7 models, inference using Qualcomm CPU, GPU, or HTP as the backend, whole-model float16 inference, activation INT16 and weights INT8 quantized inference, and activation INT16 and weights INT4/INT8 mixed quantized inference. Users can convert model weights to QNN model library files, generate HTP context cache, and run inference on Qualcomm Snapdragon SM8650 with HTP v75. The project requires QNN SDK, AIMET toolkit, and specific hardware for verification.

A repository sharing literatures and resources about Large Language Models (LLMs) and beyond. It includes tutorials, notebooks, course assignments, development stages, modeling, inference, training, applications, study, and basics related to LLMs. The repository covers various topics such as language models, transformers, state space models, multi-modal language models, training recipes, applications in autonomous driving, code, math, embodied intelligence, and more. The content is organized by different categories and provides comprehensive information on LLMs and related topics.

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.

Llama3.java is a practical Llama 3 inference tool implemented in a single Java file. It serves as the successor of llama2.java and is designed for testing and tuning compiler optimizations and features on the JVM, especially for the Graal compiler. The tool features a GGUF format parser, Llama 3 tokenizer, Grouped-Query Attention inference, support for Q8_0 and Q4_0 quantizations, fast matrix-vector multiplication routines using Java's Vector API, and a simple CLI with 'chat' and 'instruct' modes. Users can download quantized .gguf files from huggingface.co for model usage and can also manually quantize to pure 'Q4_0'. The tool requires Java 21+ and supports running from source or building a JAR file for execution. Performance benchmarks show varying tokens/s rates for different models and implementations on different hardware setups.

AIMET is a library that provides advanced model quantization and compression techniques for trained neural network models. It provides features that have been proven to improve run-time performance of deep learning neural network models with lower compute and memory requirements and minimal impact to task accuracy. AIMET is designed to work with PyTorch, TensorFlow and ONNX models. We also host the AIMET Model Zoo - a collection of popular neural network models optimized for 8-bit inference. We also provide recipes for users to quantize floating point models using AIMET.

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.

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!

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.

AutoGPTQ is an easy-to-use LLM quantization package with user-friendly APIs, based on GPTQ algorithm (weight-only quantization). It provides a simple and efficient way to quantize large language models (LLMs) to reduce their size and computational cost while maintaining their performance. AutoGPTQ supports a wide range of LLM models, including GPT-2, GPT-J, OPT, and BLOOM. It also supports various evaluation tasks, such as language modeling, sequence classification, and text summarization. With AutoGPTQ, users can easily quantize their LLM models and deploy them on resource-constrained devices, such as mobile phones and embedded systems.

GPTQModel is an easy-to-use LLM quantization and inference toolkit based on the GPTQ algorithm. It provides support for weight-only quantization and offers features such as dynamic per layer/module flexible quantization, sharding support, and auto-heal quantization errors. The toolkit aims to ensure inference compatibility with HF Transformers, vLLM, and SGLang. It offers various model supports, faster quant inference, better quality quants, and security features like hash check of model weights. GPTQModel also focuses on faster quantization, improved quant quality as measured by PPL, and backports bug fixes from AutoGPTQ.

The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud. It provides a Plain C/C++ implementation without any dependencies, optimized for Apple silicon via ARM NEON, Accelerate and Metal frameworks, and supports various architectures like AVX, AVX2, AVX512, and AMX. It offers integer quantization for faster inference, custom CUDA kernels for NVIDIA GPUs, Vulkan and SYCL backend support, and CPU+GPU hybrid inference. llama.cpp is the main playground for developing new features for the ggml library, supporting various models and providing tools and infrastructure for LLM deployment.

Qwen-TensorRT-LLM is a project developed for the NVIDIA TensorRT Hackathon 2023, focusing on accelerating inference for the Qwen-7B-Chat model using TRT-LLM. The project offers various functionalities such as FP16/BF16 support, INT8 and INT4 quantization options, Tensor Parallel for multi-GPU parallelism, web demo setup with gradio, Triton API deployment for maximum throughput/concurrency, fastapi integration for openai requests, CLI interaction, and langchain support. It supports models like qwen2, qwen, and qwen-vl for both base and chat models. The project also provides tutorials on Bilibili and blogs for adapting Qwen models in NVIDIA TensorRT-LLM, along with hardware requirements and quick start guides for different model types and quantization methods.

AutoRound is an advanced weight-only quantization algorithm for low-bits LLM inference. It competes impressively against recent methods without introducing any additional inference overhead. The method adopts sign gradient descent to fine-tune rounding values and minmax values of weights in just 200 steps, often significantly outperforming SignRound with the cost of more tuning time for quantization. AutoRound is tailored for a wide range of models and consistently delivers noticeable improvements.

ExLlamaV2 is an inference library designed for running local LLMs on modern consumer GPUs. The library supports paged attention via Flash Attention 2.5.7+, offers a new dynamic generator with features like dynamic batching, smart prompt caching, and K/V cache deduplication. It also provides an API for local or remote inference using TabbyAPI, with extended features like HF model downloading and support for HF Jinja2 chat templates. ExLlamaV2 aims to optimize performance and speed across different GPU models, with potential future optimizations and variations in speeds. The tool can be integrated with TabbyAPI for OpenAI-style web API compatibility and supports a standalone web UI called ExUI for single-user interaction with chat and notebook modes. ExLlamaV2 also offers support for text-generation-webui and lollms-webui through specific loaders and bindings.

This repository contains the training and inference code needed to replicate the winning solution to the AI Mathematical Olympiad - Progress Prize 1. It consists of fine-tuning DeepSeekMath-Base 7B, high-quality training datasets, a self-consistency decoding algorithm, and carefully chosen validation sets. The training methodology involves Chain of Thought (CoT) and Tool Integrated Reasoning (TIR) training stages. Two datasets, NuminaMath-CoT and NuminaMath-TIR, were used to fine-tune the models. The models were trained using open-source libraries like TRL, PyTorch, vLLM, and DeepSpeed. Post-training quantization to 8-bit precision was done to improve performance on Kaggle's T4 GPUs. The project structure includes scripts for training, quantization, and inference, along with necessary installation instructions and hardware/software specifications.

lm.rs is a tool that allows users to run inference on Language Models locally on the CPU using Rust. It supports LLama3.2 1B and 3B models, with a WebUI also available. The tool provides benchmarks and download links for models and tokenizers, with recommendations for quantization options. Users can convert models from Google/Meta on huggingface using provided scripts. The tool can be compiled with cargo and run with various arguments for model weights, tokenizer, temperature, and more. Additionally, a backend for the WebUI can be compiled and run to connect via the web interface.

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

Jlama is a modern Java inference engine designed for large language models. It supports various model types such as Gemma, Llama, Mistral, GPT-2, BERT, and more. The tool implements features like Flash Attention, Mixture of Experts, and supports different model quantization formats. Built with Java 21 and utilizing the new Vector API for faster inference, Jlama allows users to add LLM inference directly to their Java applications. The tool includes a CLI for running models, a simple UI for chatting with LLMs, and examples for different model types.