CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
☆380Nov 15, 2025Updated 7 months ago
Alternatives and similar repositories for cifar10-airbench
Users that are interested in cifar10-airbench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NanoGPT (124M) in 90 seconds☆5,409Updated this week
- Implementation of PSGD optimizer in JAX☆35Dec 31, 2024Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated 10 months ago
- Custom triton kernels for training Karpathy's nanoGPT.☆19Oct 21, 2024Updated last year
- supporting pytorch FSDP for optimizers☆84Dec 8, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆198May 30, 2026Updated 2 weeks ago
- CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.☆78Oct 17, 2025Updated 8 months ago
- ☆34Jan 25, 2024Updated 2 years ago
- 🧱 Modula software package☆335Aug 18, 2025Updated 10 months ago
- Muon is an optimizer for hidden layers in neural networks☆2,664May 24, 2026Updated 3 weeks ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,303Dec 18, 2024Updated last year
- An implementation of PSGD Kron second-order optimizer for PyTorch☆102Jul 24, 2025Updated 10 months ago
- Schedule-Free Optimization in PyTorch☆2,301May 18, 2026Updated last month
- ☆22Jan 23, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Efficient optimizers☆334Updated this week
- Synthetic Alphabet Dataset☆19Mar 27, 2025Updated last year
- Code for the paper "Function-Space Learning Rates"☆24Jun 3, 2025Updated last year
- KANs and MLPs☆12Jun 7, 2024Updated 2 years ago
- Dion optimizer algorithm☆486Jun 8, 2026Updated last week
- ☆30May 17, 2026Updated last month
- Optimization algorithm which fits a ResNet to CIFAR-10 5x faster than SGD / Adam (with terrible generalization)☆14Oct 20, 2023Updated 2 years ago
- ☆53Jun 10, 2024Updated 2 years ago
- DeMo: Decoupled Momentum Optimization☆202Dec 2, 2024Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆635Jul 1, 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…☆357Jul 29, 2024Updated last year
- Official implementation of 'A Large-Scale Exploration of mu-Transfer'☆32Jun 5, 2025Updated last year
- WIP☆96Aug 13, 2024Updated last year
- Learning ReLU INRs with B-spline wavelets.☆14Jun 5, 2024Updated 2 years ago
- 4-bit Shampoo for Memory-Efficient Network Training (NeurIPS 2024)☆13Feb 13, 2025Updated last year
- ☆27May 3, 2024Updated 2 years ago
- LLM training in simple, raw C/CUDA☆15Dec 5, 2024Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆196Jan 19, 2026Updated 4 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Focused on fast experimentation and simplicity☆79Dec 24, 2024Updated last year
- Switch EMA: A Free Lunch for Better Flatness and Sharpness☆28Feb 16, 2024Updated 2 years ago
- Official Pytorch Implementation of Self-emerging Token Labeling☆35Mar 27, 2024Updated 2 years ago
- ☆270Dec 2, 2024Updated last year
- Python library for argument and configuration management☆57Feb 7, 2023Updated 3 years ago
- Code for AAAI 2024 paper: CR-SAM: Curvature Regularized Sharpness-Aware Minimization☆12Nov 29, 2024Updated last year
- ☆15Mar 2, 2025Updated last year