Stars
Elana: A Simple Energy & Latency Analyzer for LLMs
Google Research
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
A Python module for getting the GPU status from NVIDA GPUs using nvidia-smi programmically in Python
[ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark
toolkitICL: An open source tool for automated OpenCL kernel execution and profiling.
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
The code for paper: Neuralpower: Predict and deploy energy-efficient convolutional neural networks
NASBench: A Neural Architecture Search Dataset and Benchmark
Pytorch implementation and demo of FAZE: Few-Shot Adaptive Gaze Estimation (ICCV 2019, oral)
Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
📓 Notes and summaries of various ML, Computer Vision & NLP papers.
Reading list for research topics in multimodal machine learning
Timeloop performs modeling, mapping and code-generation for tensor algebra workloads on various accelerator architectures.
Benchmarking Deep Learning operations on different hardware
Neural Network Tools: Converter and Analyzer. For caffe, pytorch, draknet and so on.
LSTM and QRNN Language Model Toolkit for PyTorch
Visualizer for neural network, deep learning and machine learning models
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
Differentiable architecture search for convolutional and recurrent networks
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
Replace original DRAM model in GPGPU-sim with Ramulator DRAM model
An open-source DRAM power model based on extensive experimental characterization of real DRAM modules. Described in the SIGMETRICS 2018 paper by Ghose et al. (https://people.inf.ethz.ch/omutlu/pub/…