Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
☆1,317Dec 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆360Jul 29, 2024Updated 2 years ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,369Jun 13, 2024Updated 2 years ago
- ☆11Sep 30, 2015Updated 11 years ago
- JAX implementation ViT-VQGAN☆67Jul 23, 2022Updated 4 years ago
- FFCV: Fast Forward Computer Vision (and other ML workloads!)☆2,995Jun 16, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,082Jul 1, 2025Updated last year
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆394Nov 15, 2025Updated 11 months ago
- Schedule-Free Optimization in PyTorch☆2,330Jul 28, 2026Updated 3 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,266Aug 22, 2025Updated last year
- Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)☆9,626Aug 26, 2026Updated 2 months ago
- Supercharge Your Model Training☆5,508Apr 29, 2026Updated 6 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,572Oct 9, 2026Updated 2 weeks ago
- A playbook for systematically maximizing the performance of deep learning models.☆30,407Jun 18, 2024Updated 2 years ago
- You like pytorch? You like micrograd? You love tinygrad! ❤️☆33,803Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆14,765Updated this week
- Official implementation of VQ-Diffusion☆985Apr 17, 2024Updated 2 years ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,021Aug 21, 2024Updated 2 years ago
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training☆24,985Aug 15, 2024Updated 2 years ago
- ####### ALERT! #########: my fork of the project has moved:☆19Dec 23, 2016Updated 9 years ago
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆156Nov 11, 2024Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆737Oct 11, 2023Updated 3 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆64,188Nov 12, 2025Updated 11 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆8,535Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights --…☆37,255Updated this week
- NanoGPT (124M) in 90 seconds☆5,976Sep 28, 2026Updated last month
- CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.☆86Jul 30, 2026Updated 2 months ago
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,343Oct 28, 2024Updated 2 years ago
- Solve puzzles. Improve your pytorch.☆4,431Jul 15, 2024Updated 2 years ago
- Inference Llama 2 in one file of pure C☆20,222Aug 6, 2024Updated 2 years ago
- A concise but complete full-attention transformer with a set of promising experimental features from various papers☆5,961Updated this week
- Fast bare-bones BPE for modern tokenizer training☆180Jun 23, 2025Updated last year
- Development repository for the Triton language and compiler☆20,473Updated this week
- 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.
- ScriptBots is an Open Source Evolutionary Artificial Life Simulation of Predator-Prey dynamics, written by Andrej Karpathy.☆20May 15, 2024Updated 2 years ago
- Fast and memory-efficient exact attention☆25,216Updated this week
- Flax is a neural network library for JAX that is designed for flexibility.☆7,359Updated this week
- Tile primitives for speedy kernels☆3,786Sep 12, 2026Updated last month
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,731Oct 7, 2026Updated 3 weeks ago
- An open source implementation of CLIP.☆14,229Updated this week
- TensorDict is a pytorch dedicated tensor container.☆1,043Updated this week