Alternatives and similar repositories for pocketnn

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

• wangmaolin / niti
  Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv
  ☆89Updated 3 years ago
• Qualcomm-AI-research / FP8-quantization
  ☆168Updated 2 years ago
• fastmachinelearning / qonnx
  QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
  ☆170Updated this week
• larq / zoo
  Reference implementations of popular Binarized Neural Networks
  ☆109Updated last week
• benja263 / Integer-Only-Inference-for-Deep-Learning-in-Native-C
  Converting a deep neural network to integer-only inference in native C via uniform quantization and the fixed-point representation.
  ☆26Updated 3 years ago
• areusch / microtvm-blogpost-eval
  ☆29Updated 4 years ago
• jafermarq / WinogradAwareNets
  Official implementation of "Searching for Winograd-aware Quantized Networks" (MLSys'20)
  ☆27Updated 2 years ago
• larq / compute-engine
  Highly optimized inference engine for Binarized Neural Networks
  ☆251Updated this week
• gplhegde / convolution-flavors
  Implementation of convolution layer in different flavors
  ☆68Updated 8 years ago
• eliberis / uNAS
  μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.
  ☆82Updated 4 years ago
• Tiiiger / QPyTorch
  Low Precision Arithmetic Simulation in PyTorch
  ☆287Updated last year
• kunglab / ebnn
  Header-only C library for Binary Neural Network Feedforward Inference (targeting small devices)
  ☆48Updated 4 years ago
• ekut-es / pico-cnn
  Lightweight C implementation of CNNs for Embedded Systems
  ☆62Updated 2 years ago
• HazyResearch / butterfly
  Butterfly matrix multiplication in PyTorch
  ☆178Updated 2 years ago
• pulp-platform / dory
  A tool to deploy Deep Neural Networks on PULP-based SoC's
  ☆91Updated 5 months ago
• pulp-platform / nemo
  NEural Minimizer for pytOrch
  ☆47Updated last year
• GreenWaves-Technologies / bfloat16
  bfloat16 dtype for numpy
  ☆20Updated 2 years ago
• iml130 / nncg
  NNCG: A Neural Network Code Generator
  ☆35Updated last year
• YulhwaKim / cutlass_tilesparse
  CUDA templates for tile-sparse matrix multiplication based on CUTLASS.
  ☆50Updated 7 years ago
• maltanar / gemmbitserial
  Fast matrix multiplication for few-bit integer matrices on CPUs.
  ☆28Updated 6 years ago
• YashasSamaga / ConvolutionBuildingBlocks
  GEMM and Winograd based convolutions using CUTLASS
  ☆28Updated 5 years ago
• anony-sub / chameleon
  Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
  ☆27Updated 6 years ago
• EEESlab / CMix-NN
  CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices
  ☆48Updated 5 years ago
• mlzxy / qsparse
  Train neural networks with joint quantization and pruning on both weights and activations using any pytorch modules
  ☆43Updated 3 years ago
• pulp-platform / quantlab
  ☆40Updated last year
• ROCm / tensorcast
  ☆15Updated 2 months ago
• DeMoriarty / custom_matmul_kernels
  Customized matrix multiplication kernels
  ☆57Updated 3 years ago
• plumerai / rethinking-bnn-optimization
  Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"
  ☆75Updated 6 years ago
• Qualcomm-AI-research / transformer-quantization
  ☆208Updated 4 years ago
• eliberis / tflite-tools
  TFLite model analyzer & memory optimizer
  ☆135Updated last year