CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.
☆82Jul 30, 2026Updated 2 months ago
Alternatives and similar repositories for cifar10-speedrun
Users that are interested in cifar10-speedrun are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆392Nov 15, 2025Updated 10 months ago
- 100M tokens. Infinite compute. Lowest val loss wins.☆560Sep 15, 2026Updated 3 weeks ago
- NanoGPT (124M) in 90 seconds☆5,923Sep 28, 2026Updated last week
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆146May 6, 2026Updated 5 months ago
- ☆18Aug 19, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Enhancing Chess Reinforcement Learning with Graph Representation☆26Sep 11, 2026Updated 3 weeks ago
- A short lecture introducing plane-wave DFT methods and DFTK☆14Jun 20, 2022Updated 4 years ago
- Code for the Avey-B paper (https://arxiv.org/abs/2602.15814)☆33Feb 21, 2026Updated 7 months ago
- supporting pytorch FSDP for optimizers☆85Dec 8, 2024Updated last year
- ☆27Oct 30, 2025Updated 11 months ago
- Framework for Algorithmic Correctness Testing of Operators☆18Mar 9, 2026Updated 6 months ago
- Muon is an optimizer for hidden layers in neural networks☆2,868May 24, 2026Updated 4 months ago
- ☆21Apr 3, 2025Updated last year
- research impl of Native Sparse Attention (2502.11089)☆62Feb 19, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Implementation of Multiscreen proposed by Ken Nakanishi for "Screening is Enough"☆19May 13, 2026Updated 4 months ago
- 2D chess pieces inspired by handmade wooden chess sets, featuring cuteness and simplicity☆15Feb 14, 2026Updated 7 months ago
- Implementation of Fast Weight Attention☆35Sep 17, 2026Updated 3 weeks ago
- A simple TUI to assist in diffing bodies of text☆15May 9, 2024Updated 2 years ago
- Structured data extraction and programmatic interaction with Lean 4.☆20May 7, 2026Updated 5 months ago
- a Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization in pure C.☆25Jul 6, 2024Updated 2 years ago
- A (UNOFFICIAL) wrapper of the SlackAPI in Julia☆16Mar 28, 2023Updated 3 years ago
- Dion optimizer algorithm☆555Sep 30, 2026Updated last week
- A code snippet that proves that there is no legal, potentially non-reachable chess position with more than 218 moves.☆23May 23, 2024Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective☆18Aug 10, 2026Updated last month
- WIP☆96Aug 13, 2024Updated 2 years ago
- Implementation of Recurrent Independent Mechanisms in Pytorch☆27Apr 6, 2026Updated 6 months ago
- ☆24Dec 11, 2021Updated 4 years ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆188May 13, 2026Updated 4 months ago
- Julia package with several functions to train and analyze Autoencoder-based neural networks☆25Mar 27, 2025Updated last year
- A lightweight, user-friendly data-plane for LLM training.☆43Sep 10, 2025Updated last year
- Video-CoM: Interactive Video Reasoning via Chain of Manipulations☆23Sep 5, 2026Updated last month
- Evolution Pretraining Fully in Int Formats☆186Feb 25, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The evaluation pipeline for the 2024 BabyLM Challenge.☆34Nov 13, 2024Updated last year
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆49Sep 2, 2025Updated last year
- A proof-of-concept implementation of Titans: models mixing long-term, short-term and persistent memories☆24Apr 9, 2025Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆207May 30, 2026Updated 4 months ago
- Extreme Learning Machine using RcppArmadillo☆15Feb 1, 2026Updated 8 months ago
- ☆17Feb 3, 2024Updated 2 years ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,311Dec 18, 2024Updated last year