KellerJordan / cifar10-airbench
CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
☆205Updated this week
Alternatives and similar repositories for cifar10-airbench:
Users that are interested in cifar10-airbench are comparing it to the libraries listed below
- ☆158Updated 2 months ago
- supporting pytorch FSDP for optimizers☆76Updated 2 months ago
- Efficient optimizers☆169Updated this week
- 🧱 Modula software package☆145Updated this week
- Normalized Transformer (nGPT)☆152Updated 3 months ago
- Muon optimizer: +~30% sample efficiency with <3% wallclock overhead☆253Updated last week
- WIP☆93Updated 6 months ago
- ☆208Updated 7 months ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆168Updated 2 months ago
- Accelerated First Order Parallel Associative Scan☆171Updated 6 months ago
- Annotated version of the Mamba paper☆473Updated 11 months ago
- DeMo: Decoupled Momentum Optimization☆180Updated 2 months ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆177Updated 5 months ago
- For optimization algorithm research and development.☆491Updated this week
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆271Updated 3 months ago
- Understand and test language model architectures on synthetic tasks.☆181Updated last month
- Implementation of Diffusion Transformer (DiT) in JAX☆265Updated 8 months ago
- ☆25Updated last year
- ☆253Updated 5 months ago
- seqax = sequence modeling + JAX☆143Updated 7 months ago
- ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).☆204Updated this week
- Flow-matching algorithms in JAX☆83Updated 6 months ago
- Experiment of using Tangent to autodiff triton☆75Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆102Updated 2 months ago
- ☆75Updated 7 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆179Updated 3 weeks ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆221Updated this week
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆126Updated last week