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.
☆1,443Updated 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
Sorting:
- A pytorch quantization backend for optimum☆995Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,834Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,438Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆766Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆916Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,525Updated last year
- The Triton TensorRT-LLM Backend☆901Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,911Updated last week
- This repository contains tutorials and examples for Triton Inference Server☆787Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆904Updated last month
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,106Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆698Updated 2 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,891Updated this week
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.☆668Updated this week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆696Updated this week
- A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆593Updated 2 months ago
- Pipeline Parallelism for PyTorch☆780Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,145Updated last month
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,318Updated 3 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,173Updated 3 weeks ago
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆828Updated last week
- Official implementation of Half-Quadratic Quantization (HQQ)☆883Updated last month
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,511Updated this week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,873Updated last week
- ONNX Optimizer☆764Updated 2 weeks ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆945Updated 9 months ago
- A parser, editor and profiler tool for ONNX models.☆458Updated 2 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆3,658Updated this week
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆745Updated last week
- Low-bit LLM inference on CPU/NPU with lookup table☆871Updated 4 months ago