KellerJordan / cifar10-airbenchLinks
CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
☆283Updated last month
Alternatives and similar repositories for cifar10-airbench
Users that are interested in cifar10-airbench are comparing it to the libraries listed below
Sorting:
- Efficient optimizers☆254Updated 2 weeks ago
- ☆208Updated 8 months ago
- 🧱 Modula software package☆222Updated 3 weeks ago
- Accelerated First Order Parallel Associative Scan☆187Updated last year
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- ☆275Updated last year
- The AdEMAMix Optimizer: Better, Faster, Older.☆184Updated 11 months ago
- Normalized Transformer (nGPT)☆186Updated 9 months ago
- A library for unit scaling in PyTorch☆129Updated last month
- Implementation of Diffusion Transformer (DiT) in JAX☆291Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆289Updated 2 months ago
- For optimization algorithm research and development.☆530Updated this week
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆389Updated this week
- Annotated version of the Mamba paper☆487Updated last year
- WIP☆94Updated last year
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆327Updated 7 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆152Updated last month
- Universal Tensor Operations in Einstein-Inspired Notation for Python.☆399Updated 4 months ago
- Dion optimizer algorithm☆291Updated last week
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆179Updated this week
- ☆87Updated last year
- Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"☆116Updated 4 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆96Updated 3 weeks ago
- ☆307Updated last year
- Getting crystal-like representations with harmonic loss☆194Updated 4 months ago
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- seqax = sequence modeling + JAX☆166Updated last month
- nanoGPT-like codebase for LLM training☆102Updated 3 months ago
- ☆56Updated 10 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆124Updated 8 months ago