whittle-org / whittleLinks
Python library to compress LitGPT models for resource efficient inference.
☆14Updated this week
Alternatives and similar repositories for whittle
Users that are interested in whittle are comparing it to the libraries listed below
Sorting:
- Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.☆410Updated last week
- A framework for QuickTune☆16Updated 6 months ago
- NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several …☆557Updated 8 months ago
- Neural Pipeline Search (NePS): Helps deep learning experts find the best neural pipeline.☆77Updated this week
- Launching and monitoring Slurm experiments in Python☆18Updated last week
- Surrogate benchmarks for HPO problems☆27Updated last month
- [ICLR 2021] Few Shot Bayesian Optimization☆20Updated 2 years ago
- NAS Benchmarks Collection☆12Updated 2 years ago
- [ICLR2024] Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How☆32Updated 8 months ago
- ☆13Updated 3 years ago
- Specificy, execute and monitor performances of active learning pipelines.☆23Updated 9 months ago
- In-context Bayesian Optimization☆16Updated 2 months ago
- [NeurIPS 2022] Supervising the Multi-Fidelity Race of Hyperparameter Configurations☆13Updated 2 years ago
- Collection of hyperparameter optimization benchmark problems☆150Updated last month
- Domain specific language for configuration spaces in Python. Useful for hyperparameter optimization and algorithm configuration.☆212Updated this week
- A Library for Uncertainty Quantification.☆918Updated 2 months ago
- Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.☆477Updated 8 months ago
- HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models☆20Updated 7 months ago
- a distributed Hyperband implementation on Steroids☆618Updated 2 years ago
- SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization☆1,183Updated this week
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆388Updated last week
- Code accompanying https://arxiv.org/abs/1802.02219☆18Updated 2 years ago
- The WeightWatcher tool for predicting the accuracy of Deep Neural Networks☆1,622Updated last month
- ☆222Updated 2 weeks ago
- ☆83Updated 2 months ago
- ☆17Updated 2 years ago
- Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.☆1,068Updated 3 weeks ago
- Library for automatic retraining and continual learning☆294Updated 9 months ago
- ☆17Updated 9 months ago
- A Living Benchmark for Machine Learning on Tabular Data☆97Updated last week