mlcommons / inferenceLinks
Reference implementations of MLPerf™ inference benchmarks
☆1,441Updated last 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☆1,702Updated this week
- Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure☆899Updated last week
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,426Updated this week
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆993Updated 11 months ago
- Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Inte…☆716Updated last week
- The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.☆1,612Updated last week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆850Updated last week
- ☆419Updated last week
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,476Updated this week
- Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators☆447Updated this week
- NCCL Tests☆1,219Updated 3 weeks ago
- TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.☆976Updated this week
- A performant and modular runtime for TensorFlow☆758Updated 2 weeks ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆886Updated 7 months ago
- Backward compatible ML compute opset inspired by HLO/MHLO☆522Updated last week
- Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…☆484Updated 2 weeks ago
- NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs☆561Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,057Updated last year
- Collective communications library with various primitives for multi-machine training.☆1,342Updated 3 weeks ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,645Updated last week
- ONNX Optimizer☆742Updated 3 weeks ago
- Dive into Deep Learning Compiler☆647Updated 3 years ago
- The Tensor Algebra SuperOptimizer for Deep Learning☆730Updated 2 years ago
- A tool for bandwidth measurements on NVIDIA GPUs.☆515Updated 4 months ago
- An open-source efficient deep learning framework/compiler, written in python.☆715Updated 3 weeks ago
- High-efficiency floating-point neural network inference operators for mobile, server, and Web☆2,086Updated this week
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆606Updated last week
- ☆392Updated 2 years ago
- A validation and profiling tool for AI infrastructure☆328Updated this week
- Optimized primitives for collective multi-GPU communication☆3,964Updated last week