NVIDIA / Model-OptimizerLinks
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
☆1,925Updated this week
Alternatives and similar repositories for Model-Optimizer
Users that are interested in Model-Optimizer are comparing it to the libraries listed below
Sorting:
- PyTorch native quantization and sparsity for training and inference☆2,657Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,132Updated this week
- A pytorch quantization backend for optimum☆1,022Updated 2 months ago
- The Triton TensorRT-LLM Backend☆918Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,005Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,600Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆810Updated 11 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,660Updated last week
- This repository contains tutorials and examples for Triton Inference Server☆815Updated this week
- FlashInfer: Kernel Library for LLM Serving☆4,853Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆945Updated 3 months ago
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆1,007Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,332Updated last week
- 🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality degradation across Weight-Only Quantiza…☆839Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,104Updated last week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆893Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,235Updated 5 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆749Updated 6 months ago
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.☆672Updated 2 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆1,067Updated last year
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,939Updated this week
- Tile primitives for speedy kernels☆3,120Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,577Updated last week
- Fast CUDA matrix multiplication from scratch☆1,040Updated 5 months ago
- Pipeline Parallelism for PyTorch☆784Updated last year
- A Quirky Assortment of CuTe Kernels☆781Updated this week
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆782Updated 3 months ago
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆682Updated last week
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆520Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆912Updated last month