NVIDIA / TensorRT-Model-Optimizer
TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.
☆708Updated 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
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆729Updated 5 months ago
- The Triton TensorRT-LLM Backend☆779Updated this week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆496Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆737Updated 5 months ago
- A pytorch quantization backend for optimum☆883Updated last month
- Pipeline Parallelism for PyTorch☆749Updated 6 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆523Updated last week
- FlashInfer: Kernel Library for LLM Serving☆2,078Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,190Updated this week
- This repository contains tutorials and examples for Triton Inference Server☆648Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆746Updated this week
- Common source, scripts and utilities for creating Triton backends.☆307Updated last week
- A parser, editor and profiler tool for ONNX models.☆414Updated last month
- FlagGems is an operator library for large language models implemented in Triton Language.☆420Updated this week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆342Updated 2 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,339Updated 7 months ago
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆772Updated last week
- PyTorch native quantization and sparsity for training and inference☆1,848Updated this week
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆407Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆514Updated this week
- Advanced Quantization Algorithm for LLMs/VLMs.☆372Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆982Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆290Updated this week
- LLM KV cache compression made easy☆397Updated this week
- Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.☆284Updated this week
- Microsoft Automatic Mixed Precision Library☆567Updated 4 months ago
- Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…☆454Updated this week
- Actively maintained ONNX Optimizer☆672Updated 3 weeks ago
- TensorRT Plugin Autogen Tool☆369Updated last year
- ☆314Updated 10 months ago