mekaneeky / Simple-AutoML-Zero
A simple numpy implementation of AutoML Zero. Currently a rough draft. Should clean up a bit.
☆9Updated last year
Alternatives and similar repositories for Simple-AutoML-Zero:
Users that are interested in Simple-AutoML-Zero are comparing it to the libraries listed below
- Forward Pass Learning and Inference Library, for neural networks and general intelligence, Signal Propagation (sigprop)☆50Updated last year
- A Plug-and-play Lightweight tool for the Inference Optimization of Deep Neural networks☆39Updated this week
- A library to train and deploy quantised Deep Neural Networks☆21Updated 2 months ago
- Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix multiplication unit☆119Updated 10 months ago
- ☆82Updated last year
- ReckOn: A Spiking RNN Processor Enabling On-Chip Learning over Second-Long Timescales - HDL source code and documentation.☆81Updated 3 years ago
- Open source machine learning accelerators☆371Updated 10 months ago
- μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.☆78Updated 4 years ago
- Research and Materials on Hardware implementation of Transformer Model☆232Updated last week
- ☆56Updated 4 years ago
- Papers and codes about Quantized Networks for easier survey and reference.☆18Updated 3 years ago
- Accelergy is an energy estimation infrastructure for accelerator energy estimations☆133Updated 2 weeks ago
- ☆34Updated 11 months ago
- Machine-Learning Accelerator System Exploration Tools☆145Updated this week
- System Verilog code describing a fully combinational binarized neural network.☆33Updated 6 years ago
- E2E AutoML Model Compression Package☆46Updated 3 weeks ago
- This is the code that went into our practical dive using mamba as information extraction☆51Updated last year
- ☆68Updated 11 months ago
- HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators☆129Updated this week
- PB-LLM: Partially Binarized Large Language Models☆151Updated last year
- Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv☆80Updated 2 years ago
- This is the implentation of our paper "SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms" in ICML…☆26Updated 7 months ago
- Liquid Structural State-Space Models☆337Updated last year
- Binarize convolutional neural networks using pytorch☆139Updated 2 years ago
- A repository for log-time feedforward networks☆219Updated 10 months ago
- ☆24Updated last year
- Torch2Chip (MLSys, 2024)☆51Updated 2 weeks ago
- Floating-Point Optimized On-Device Learning Library for the PULP Platform.☆30Updated 2 months ago
- Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).☆111Updated 4 months ago
- Open source version of ArchGym project.☆111Updated this week