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
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…☆359Jul 29, 2024Updated 2 years ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,368Jun 13, 2024Updated 2 years ago
- FFCV: Fast Forward Computer Vision (and other ML workloads!)☆2,994Jun 16, 2024Updated 2 years ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆386Nov 15, 2025Updated 8 months ago
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,086Jul 1, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Schedule-Free Optimization in PyTorch☆2,323Jul 28, 2026Updated last week
- Supercharge Your Model Training☆5,494Apr 29, 2026Updated 3 months ago
- Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)☆9,570Jul 5, 2026Updated last month
- A playbook for systematically maximizing the performance of deep learning models.☆30,277Jun 18, 2024Updated 2 years ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,244Aug 22, 2025Updated 11 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,540Updated this week
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆14,655Jul 23, 2026Updated 2 weeks ago
- JAX implementation ViT-VQGAN☆66Jul 23, 2022Updated 4 years ago
- You like pytorch? You like micrograd? You love tinygrad! ❤️☆33,431Updated this week
- 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.
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,021Aug 21, 2024Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆8,411Updated this week
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training☆24,787Aug 15, 2024Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆62,005Nov 12, 2025Updated 8 months ago
- The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights --…☆37,057Updated this week
- A concise but complete full-attention transformer with a set of promising experimental features from various papers☆5,932Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,358Oct 28, 2024Updated last year
- Inference Llama 2 in one file of pure C☆19,958Aug 6, 2024Updated 2 years ago
- An open source implementation of CLIP.☆14,051Jul 31, 2026Updated last 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.
- Official implementation of VQ-Diffusion☆983Apr 17, 2024Updated 2 years ago
- Monte Carlo tree search in JAX☆2,650Updated this week
- Fast and memory-efficient exact attention☆24,672Updated this week
- Solve puzzles. Improve your pytorch.☆4,275Jul 15, 2024Updated 2 years ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,198Jul 9, 2026Updated last month
- Development repository for the Triton language and compiler☆19,919Updated this week
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.☆3,512May 19, 2025Updated last year
- NanoGPT (124M) in 90 seconds☆5,658Updated this week
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,898Jun 22, 2025Updated last year
- 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.
- Flax is a neural network library for JAX that is designed for flexibility.☆7,300Updated this week
- OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamical…☆37,402Aug 17, 2024Updated last year
- Solve puzzles. Learn CUDA.☆12,393Sep 1, 2024Updated last year
- What would you do with 1000 H100s...☆1,188Jan 10, 2024Updated 2 years ago
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM☆7,864Jul 27, 2026Updated 2 weeks ago
- ☆315Jun 21, 2024Updated 2 years ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,726Updated this week