Alternatives and similar repositories for inference

Users that are interested in inference are comparing it to the libraries listed below

• mlcommons / training
  Reference implementations of MLPerf™ training benchmarks
  ☆1,683Updated last month
• intel / neural-compressor
  SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…
  ☆2,430Updated this week
• pytorch / FBGEMM
  FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
  ☆1,383Updated this week
• onnx / onnx-mlir
  Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure
  ☆873Updated last week
• microsoft / nnfusion
  A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.
  ☆989Updated 9 months ago
• alibaba / BladeDISC
  BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.
  ☆873Updated 5 months ago
• jiazhihao / TASO
  The Tensor Algebra SuperOptimizer for Deep Learning
  ☆715Updated 2 years ago
• tensorflow / runtime
  A performant and modular runtime for TensorFlow
  ☆762Updated 2 months ago
• pytorch / torchdynamo
  A Python-level JIT compiler designed to make unmodified PyTorch programs faster.
  ☆1,051Updated last year
• NVIDIA / TransformerEngine
  A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…
  ☆2,491Updated this week
• NVIDIA / DCGM
  NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs
  ☆525Updated last month
• onnx / optimizer
  ONNX Optimizer
  ☆721Updated last week
• flexflow / flexflow-train
  Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training
  ☆1,803Updated this week
• tensorflow / mlir-hlo
  ☆416Updated this week
• NVIDIA / nccl-tests
  NCCL Tests
  ☆1,149Updated 2 weeks ago
• d2l-ai / d2l-tvm
  Dive into Deep Learning Compiler
  ☆644Updated 3 years ago
• llvm / torch-mlir
  The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
  ☆1,562Updated last week
• triton-inference-server / model_analyzer
  Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…
  ☆477Updated last week
• pytorch / kineto
  A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
  ☆821Updated this week
• dmlc / dlpack
  common in-memory tensor structure
  ☆1,014Updated last week
• pytorch / benchmark
  TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.
  ☆948Updated 2 weeks ago
• intel / ai-reference-models
  Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Inte…
  ☆718Updated last week
• pytorch / gloo
  Collective communications library with various primitives for multi-machine training.
  ☆1,315Updated this week
• pytorch / TensorRT
  PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
  ☆2,783Updated this week
• msr-fiddle / pipedream
  ☆391Updated 2 years ago
• NVIDIA / TensorRT-Model-Optimizer
  A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …
  ☆995Updated this week
• google / XNNPACK
  High-efficiency floating-point neural network inference operators for mobile, server, and Web
  ☆2,046Updated this week
• uxlfoundation / oneDNN
  oneAPI Deep Neural Network Library (oneDNN)
  ☆3,813Updated this week
• NVIDIA / nccl
  Optimized primitives for collective multi-GPU communication
  ☆3,789Updated 3 weeks ago
• quic / aimet
  AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
  ☆2,340Updated this week