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
  ☆80Updated 2 years ago
• IntelLabs / FP8-Emulation-Toolkit
  PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.
  ☆108Updated 4 months ago
• jafermarq / WinogradAwareNets
  Official implementation of "Searching for Winograd-aware Quantized Networks" (MLSys'20)
  ☆27Updated last year
• areusch / microtvm-blogpost-eval
  ☆29Updated 4 years ago
• gplhegde / convolution-flavors
  Implementation of convolution layer in different flavors
  ☆68Updated 7 years ago
• YulhwaKim / cutlass_tilesparse
  CUDA templates for tile-sparse matrix multiplication based on CUTLASS.
  ☆51Updated 7 years ago
• maltanar / gemmbitserial
  Fast matrix multiplication for few-bit integer matrices on CPUs.
  ☆27Updated 6 years ago
• Qualcomm-AI-research / FP8-quantization
  ☆143Updated 2 years ago
• YashasSamaga / ConvolutionBuildingBlocks
  GEMM and Winograd based convolutions using CUTLASS
  ☆26Updated 4 years ago
• brightlaboratory / polydl
  ☆12Updated 3 years ago
• wjc852456 / Neural-Networks-on-Silicon
  This is a collection of works on neural networks and neural accelerators.
  ☆40Updated 6 years ago
• EECS-NTNU / bismo
  BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing
  ☆137Updated 5 years ago
• max2ma / shiftNet
  ☆14Updated 5 years ago
• minhhn2910 / QPyTorch
  Low Precision Arithmetic Simulation in PyTorch - extension for posit and beyond
  ☆13Updated last year
• limenghao / AdaTune
  This is the implementation for paper: AdaTune: Adaptive Tensor Program CompilationMade Efficient (NeurIPS 2020).
  ☆13Updated 3 years ago
• gilshm / sparq
  Post-training sparsity-aware quantization
  ☆34Updated 2 years ago
• sfox14 / block_minifloat
  Training with Block Minifloat number representation
  ☆14Updated 3 years ago
• EEESlab / CMix-NN
  CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices
  ☆41Updated 5 years ago
• camlsys / torchquant
  A Hackable Quantization Library for PyTorch
  ☆20Updated 4 years ago
• mrusci / training-mixed-precision-quantized-networks
  This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contr…
  ☆49Updated 11 months ago
• Zhen-Dong / CoDeNet
  [FPGA'21] CoDeNet is an efficient object detection model on PyTorch, with SOTA performance on VOC and COCO based on CenterNet and Co-Desi…
  ☆25Updated 2 years ago
• IBM / pfloat
  A 8-/16-/32-/64-bit floating point number family
  ☆17Updated 3 years ago
• EEESlab / CMSIS_NN-INTQ
  INT-Q Extension of the CMSIS-NN library for ARM Cortex-M target
  ☆18Updated 5 years ago
• ehw-fit / tf-approximate
  Approximate layers - TensorFlow extension
  ☆27Updated last week
• pulp-platform / dory
  A tool to deploy Deep Neural Networks on PULP-based SoC's
  ☆80Updated 2 months ago
• pulp-platform / quantlab
  ☆36Updated last year
• ROCm / tensorcast
  ☆11Updated this week
• eliberis / uNAS
  μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.
  ☆81Updated 4 years ago
• AMDResearch / Riallto
  The Riallto Open Source Project from AMD
  ☆77Updated 2 weeks ago
• parsa-epfl / HBFPEmulator
  ColTraIn HBFP Training Emulator
  ☆16Updated 2 years ago