NVIDIA / TensorRT-Model-Optimizer
TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.
☆667Updated last week
Alternatives and similar repositories for TensorRT-Model-Optimizer:
Users that are interested in TensorRT-Model-Optimizer are comparing it to the libraries listed below
- The Triton TensorRT-LLM Backend☆745Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆680Updated 4 months ago
- A pytorch quantization backend for optimum☆865Updated last week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆481Updated 2 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,086Updated this week
- Pipeline Parallelism for PyTorch☆736Updated 4 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,797Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆692Updated 3 months ago
- This repository contains tutorials and examples for Triton Inference Server☆623Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆496Updated this week
- A parser, editor and profiler tool for ONNX models.☆411Updated last week
- Microsoft Automatic Mixed Precision Library☆549Updated 3 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,316Updated 6 months ago
- TensorRT Plugin Autogen Tool☆369Updated last year
- Advanced Quantization Algorithm for LLMs/VLMs.☆344Updated this week
- Common utilities for ONNX converters☆256Updated last month
- Applied AI experiments and examples for PyTorch☆211Updated this week
- FlagGems is an operator library for large language models implemented in Triton Language.☆397Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆714Updated this week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆315Updated last month
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆505Updated 2 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆732Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆299Updated 3 weeks ago
- Actively maintained ONNX Optimizer☆657Updated 10 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆229Updated 7 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆851Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆467Updated 10 months ago
- Ring attention implementation with flash attention☆645Updated 3 weeks ago
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆763Updated last month
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆484Updated 3 weeks ago