KellerJordan / cifar10-airbenchView external linksLinks
CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
☆352Nov 15, 2025Updated 3 months ago
Alternatives and similar repositories for cifar10-airbench
Users that are interested in cifar10-airbench are comparing it to the libraries listed below
Sorting:
- NanoGPT (124M) in 2 minutes☆4,624Updated this week
- Implementation of PSGD optimizer in JAX☆35Dec 31, 2024Updated last year
- supporting pytorch FSDP for optimizers☆84Dec 8, 2024Updated last year
- Custom triton kernels for training Karpathy's nanoGPT.☆19Oct 21, 2024Updated last year
- Muon is an optimizer for hidden layers in neural networks☆2,290Jan 19, 2026Updated 3 weeks ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆190Jan 11, 2026Updated last month
- CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.☆56Oct 17, 2025Updated 4 months ago
- ☆34Jan 25, 2024Updated 2 years ago
- 🧱 Modula software package☆322Aug 18, 2025Updated 5 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆98Jul 24, 2025Updated 6 months ago
- Efficient optimizers☆283Dec 20, 2025Updated last month
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,299Dec 18, 2024Updated last year
- ☆21Jan 23, 2024Updated 2 years ago
- Schedule-Free Optimization in PyTorch☆2,256May 21, 2025Updated 8 months ago
- ☆27May 3, 2024Updated last year
- LLM training in simple, raw C/CUDA☆15Dec 5, 2024Updated last year
- Switch EMA: A Free Lunch for Better Flatness and Sharpness☆28Feb 16, 2024Updated 2 years ago
- Synthetic Alphabet Dataset☆19Mar 27, 2025Updated 10 months ago
- ☆52Jun 10, 2024Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆355Jul 29, 2024Updated last year
- WIP☆93Aug 13, 2024Updated last year
- Code for the paper "Function-Space Learning Rates"☆25Jun 3, 2025Updated 8 months ago
- Official Pytorch Implementation of Self-emerging Token Labeling☆35Mar 27, 2024Updated last year
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆67Apr 24, 2024Updated last year
- Official Implementation of Infinite-Resolution Integral Noise Warping for Diffusion Models [ICLR 2025]☆15Mar 15, 2025Updated 11 months ago
- KANs and MLPs☆12Jun 7, 2024Updated last year
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆632Jul 1, 2024Updated last year
- ☆250Dec 2, 2024Updated last year
- Focused on fast experimentation and simplicity☆80Dec 24, 2024Updated last year
- Grams: Gradient Descent with Adaptive Momentum Scaling (ICLR 2025 Workshop)☆17Mar 6, 2025Updated 11 months ago
- ☆13Jul 19, 2022Updated 3 years ago
- ☆292Jul 15, 2024Updated last year
- DeMo: Decoupled Momentum Optimization☆198Dec 2, 2024Updated last year
- Experiment of using Tangent to autodiff triton☆82Jan 22, 2024Updated 2 years ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Dec 22, 2024Updated last year
- Dion optimizer algorithm☆438Jan 16, 2026Updated last month
- ☆24Jun 4, 2024Updated last year
- Optimization algorithm which fits a ResNet to CIFAR-10 5x faster than SGD / Adam (with terrible generalization)☆14Oct 20, 2023Updated 2 years ago
- Code for AAAI 2024 paper: CR-SAM: Curvature Regularized Sharpness-Aware Minimization☆13Nov 29, 2024Updated last year