Fast, Numerically Stable, and Auto-Differentiable Spectral Clipping via Newton-Schulz Iteration
☆12Jun 21, 2025Updated last year
Alternatives and similar repositories for spectral_clip
Users that are interested in spectral_clip are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated last year
- Maximal Update Parametrization (μP) with Flax & Optax.☆16Dec 27, 2023Updated 2 years ago
- Pytorch/XLA SPMD Test code in Google TPU☆23Apr 3, 2024Updated 2 years ago
- Automatically take good care of your preemptible TPUs☆37May 15, 2023Updated 3 years ago
- T5 model optimized with FlexAttention☆14Sep 30, 2024Updated 2 years ago
- 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.
- Dataloader designed for JAX without any other dependencies☆15Feb 28, 2026Updated 8 months ago
- Don't just regulate gradients like in Muon, regulate the weights too☆32Jul 30, 2025Updated last year
- ☆13Nov 14, 2024Updated last year
- Visual node-based model merging tool for Stable Diffusion XL☆15Apr 6, 2026Updated 6 months ago
- Implementation of PSGD optimizer in JAX☆41Dec 31, 2024Updated last year
- research impl of Native Sparse Attention (2502.11089)☆63Feb 19, 2025Updated last year
- SMT-encodable GPT-2 variant with formal guarantees☆14Jul 29, 2026Updated 3 months ago
- ☆16May 24, 2026Updated 5 months ago
- Code for OGB competition☆12Feb 24, 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.
- Flash Attention in 300-500 lines of CUDA/C++☆39Aug 22, 2025Updated last year
- implementation of https://arxiv.org/pdf/2312.09299☆21Jul 3, 2024Updated 2 years ago
- Dynamical low rank training for neural networks☆11Aug 24, 2023Updated 3 years ago
- Algorithms from the book "Elements of Statistical Learning", implemented in Python☆14Mar 29, 2015Updated 11 years ago
- Unofficial PyTorch implementation of the Contrast Adaptative Sharpening (CAS) featured in AMD's FidelityFX.☆15Oct 20, 2026Updated last week
- ☆10Jul 27, 2026Updated 3 months ago
- ☆17Jun 16, 2026Updated 4 months ago
- A repo based on XiLin Li's PSGD repo that extends some of the experiments.☆13Oct 7, 2024Updated 2 years ago
- 4-bit Shampoo for Memory-Efficient Network Training (NeurIPS 2024)☆13Feb 13, 2025Updated last year
- 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.
- ☆14Jul 13, 2025Updated last year
- ☆19Dec 4, 2025Updated 10 months ago
- ☆11Sep 25, 2024Updated 2 years ago
- ☆15Jun 16, 2026Updated 4 months ago
- A fully trainable state space model (SSM)☆16Mar 18, 2025Updated last year
- KANs and MLPs☆12Jun 7, 2024Updated 2 years ago
- A simple PyTorch implementation of CLIP model using DinoV2 and BERT☆16Sep 26, 2023Updated 3 years ago
- Bullseye Polytope Clean-Label Poisoning Attack☆18Nov 5, 2020Updated 5 years ago
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Train to 94% on CIFAR-10 in 4.4 seconds on a single A100☆12Dec 30, 2023Updated 2 years ago
- Fully customizable Classifer Free Guidance for ComfyUI☆15Jul 14, 2024Updated 2 years ago
- ☆13Apr 16, 2024Updated 2 years ago
- ☆13Apr 25, 2024Updated 2 years ago
- Make an existing proof easier to inspect by exposing its hierarchy, dependencies, scope, and unresolved obligations.☆22Sep 6, 2026Updated last month
- ☆18Aug 24, 2024Updated 2 years ago
- Official Pytorch implementation of Chromatic Graph Transformers☆10Jun 14, 2023Updated 3 years ago