NVIDIA / TensorRT-Model-OptimizerLinks
A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed.
☆1,512Updated this 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
Sorting:
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,883Updated last week
- PyTorch native quantization and sparsity for training and inference☆2,489Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆775Updated 8 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆924Updated last year
- The Triton TensorRT-LLM Backend☆905Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,543Updated last year
- A pytorch quantization backend for optimum☆1,006Updated 2 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆912Updated 2 weeks ago
- This repository contains tutorials and examples for Triton Inference Server☆797Updated this week
- FlashInfer: Kernel Library for LLM Serving☆4,019Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,215Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,214Updated 3 weeks ago
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, …☆2,520Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆708Updated 3 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆749Updated this week
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.☆701Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,942Updated this week
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆860Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,165Updated 2 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆961Updated 10 months ago
- Pipeline Parallelism for PyTorch☆781Updated last year
- ONNX Optimizer☆770Updated last week
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆614Updated this week
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆756Updated 3 weeks ago
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆638Updated this week
- A Quirky Assortment of CuTe Kernels☆651Updated last week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆885Updated this week
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆490Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,332Updated 3 months ago
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆824Updated 2 months ago