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
Alternatives and similar repositories for hlb-CIFAR10
Users that are interested in hlb-CIFAR10 are comparing it to the libraries listed below
Sorting:
- Cramming the training of a (BERT-type) language model into limited compute.☆1,363Jun 13, 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
- FFCV: Fast Forward Computer Vision (and other ML workloads!)☆2,986Jun 16, 2024Updated last year
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,081Jul 1, 2025Updated 7 months ago
- Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)☆9,401Feb 20, 2026Updated last week
- Schedule-Free Optimization in PyTorch☆2,256May 21, 2025Updated 9 months ago
- A playbook for systematically maximizing the performance of deep learning models.☆29,861Jun 18, 2024Updated last year
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆359Nov 15, 2025Updated 3 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆7,997Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆53,743Nov 12, 2025Updated 3 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,017Aug 21, 2024Updated last year
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆14,375Feb 21, 2026Updated last week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,184Aug 22, 2025Updated 6 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,353Feb 20, 2026Updated last week
- You like pytorch? You like micrograd? You love tinygrad! ❤️☆31,424Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,383Oct 28, 2024Updated last year
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training☆23,667Aug 15, 2024Updated last year
- The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights --…☆36,397Updated this week
- JAX implementation ViT-VQGAN☆63Jul 23, 2022Updated 3 years ago
- Fast and memory-efficient exact attention☆22,361Updated this week
- An open source implementation of CLIP.☆13,430Updated this week
- Inference Llama 2 in one file of pure C☆19,186Aug 6, 2024Updated last year
- Monte Carlo tree search in JAX☆2,591Sep 2, 2025Updated 5 months ago
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.☆3,368May 19, 2025Updated 9 months ago
- What would you do with 1000 H100s...☆1,154Jan 10, 2024Updated 2 years ago
- NanoGPT (124M) in 2 minutes☆4,679Updated this week
- Official implementation of VQ-Diffusion☆978Apr 17, 2024Updated last year
- A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API☆14,774Aug 8, 2024Updated last year
- ☆316Jun 21, 2024Updated last year
- Foundation Architecture for (M)LLMs☆3,135Apr 11, 2024Updated last year
- Flax is a neural network library for JAX that is designed for flexibility.☆7,082Feb 22, 2026Updated last week
- Solve puzzles. Learn CUDA.☆11,959Sep 1, 2024Updated last year
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,869Jun 22, 2025Updated 8 months ago
- Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/☆2,792Updated this week
- maximal update parametrization (µP)☆1,686Jul 17, 2024Updated last year
- Solve puzzles. Improve your pytorch.☆3,950Jul 15, 2024Updated last year
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,706Jan 12, 2026Updated last month
- Development repository for the Triton language and compiler☆18,460Feb 22, 2026Updated last week
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,585Jan 28, 2026Updated last month