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.
☆1,848Updated last week
Alternatives and similar repositories for Model-Optimizer
Users that are interested in Model-Optimizer are comparing it to the libraries listed below
Sorting:
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,116Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,645Updated this week
- The Triton TensorRT-LLM Backend☆917Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆992Updated last year
- A pytorch quantization backend for optimum☆1,020Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆806Updated 10 months ago
- This repository contains tutorials and examples for Triton Inference Server☆815Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,590Updated last year
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,615Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆940Updated 2 months ago
- FlashInfer: Kernel Library for LLM Serving☆4,707Updated last week
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆982Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,315Updated last month
- 🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality degradation across Weight-Only Quantiza…☆830Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,231Updated 4 months ago
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,574Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆747Updated 5 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,091Updated this week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆880Updated this week
- Pipeline Parallelism for PyTorch☆785Updated last year
- Flash Attention in ~100 lines of CUDA (forward pass only)☆1,047Updated last year
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.☆669Updated 2 months ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,928Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,420Updated 6 months ago
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆680Updated last month
- ONNX Optimizer☆793Updated last week
- A Quirky Assortment of CuTe Kernels☆761Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆907Updated last month
- Neural Network Compression Framework for enhanced OpenVINO™ inference☆1,119Updated last week
- LLM KV cache compression made easy☆858Updated this week