NVIDIA / TensorRT-Model-Optimizer
nvidia-modelopt is 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.
☆900Updated 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
- A pytorch quantization backend for optimum☆927Updated 2 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆812Updated 8 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,393Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆656Updated 2 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,399Updated 9 months ago
- A throughput-oriented high-performance serving framework for LLMs☆804Updated last week
- The Triton TensorRT-LLM Backend☆832Updated last week
- Advanced Quantization Algorithm for LLMs/VLMs.☆449Updated last week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,089Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,015Updated this week
- Pipeline Parallelism for PyTorch☆765Updated 8 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆601Updated last week
- FlashInfer: Kernel Library for LLM Serving☆2,788Updated this week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆383Updated 5 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,301Updated this week
- FlagGems is an operator library for large language models implemented in Triton Language.☆516Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆536Updated last week
- Distributed Triton for Parallel Systems☆644Updated this week
- Flash Attention in ~100 lines of CUDA (forward pass only)☆803Updated 4 months ago
- This repository contains tutorials and examples for Triton Inference Server☆692Updated 3 weeks ago
- Fast low-bit matmul kernels in Triton☆295Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆820Updated this week
- Microsoft Automatic Mixed Precision Library☆596Updated 7 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆912Updated 3 weeks ago
- Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators☆393Updated this week
- LLM KV cache compression made easy☆471Updated this week
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆466Updated last week
- A parser, editor and profiler tool for ONNX models.☆430Updated 3 months ago
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆657Updated 2 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆364Updated 2 weeks ago