Reference implementations of MLPerf® inference benchmarks
☆1,535Updated this week
Alternatives and similar repositories for inference
Users that are interested in inference are comparing it to the libraries listed below
Sorting:
- Reference implementations of MLPerf® training benchmarks☆1,741Feb 20, 2026Updated last week
- Issues related to MLPerf® Inference policies, including rules and suggested changes☆63Feb 4, 2026Updated 3 weeks ago
- Open Machine Learning Compiler Framework☆13,142Updated this week
- Development repository for the Triton language and compiler☆18,460Updated this week
- Benchmarking Deep Learning operations on different hardware☆1,102Apr 25, 2021Updated 4 years ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆1,006Sep 19, 2024Updated last year
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,315Updated this week
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆12,723Updated this week
- Compiler for Neural Network hardware accelerators☆3,324May 11, 2024Updated last year
- Transformer related optimization, including BERT, GPT☆6,394Mar 27, 2024Updated last year
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆10,375Feb 21, 2026Updated last week
- oneAPI Deep Neural Network Library (oneDNN)☆3,956Updated this week
- Optimized primitives for collective multi-GPU communication☆4,474Updated this week
- Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure☆976Feb 20, 2026Updated last week
- The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.☆1,754Updated 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…☆3,170Feb 21, 2026Updated last week
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,563Updated this week
- Ongoing research training transformer models at scale☆15,242Feb 21, 2026Updated last week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,585Feb 20, 2026Updated last week
- Open Neural Network Compiler☆528Aug 22, 2023Updated 2 years ago
- FlashInfer: Kernel Library for LLM Serving☆5,009Updated this week
- MLCube® is a project that reduces friction for machine learning by ensuring that models are easily portable and reproducible.☆158Nov 26, 2025Updated 3 months ago
- This repository is outdated! Join the open MLPerf workgroup to participate in the development of the next generation of automation workfl…☆31Sep 23, 2022Updated 3 years ago
- A retargetable MLIR-based machine learning compiler and runtime toolkit.☆3,614Updated this week
- TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.☆1,014Updated this week
- This repository contains the results and code for the MLPerf™ Inference v1.0 benchmark.☆32Jul 24, 2025Updated 7 months ago
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆12,938Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,075Apr 17, 2024Updated last year
- NCCL Tests☆1,441Feb 9, 2026Updated 2 weeks ago
- To make it easy to benchmark AI accelerators☆194Dec 27, 2022Updated 3 years ago
- A list of awesome compiler projects and papers for tensor computation and deep learning.☆2,731Oct 19, 2024Updated last year
- NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs☆671Feb 17, 2026Updated last week
- State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enter…☆14,735Aug 12, 2024Updated last year
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,534Updated this week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,706Jan 12, 2026Updated last month
- Open standard for machine learning interoperability☆20,373Updated this week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,861Feb 20, 2026Updated last week
- common in-memory tensor structure☆1,169Jan 26, 2026Updated last month
- ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator☆19,389Updated this week