evanatyourservice / kron_torch
An implementation of PSGD Kron second-order optimizer for PyTorch
☆83Updated last month
Alternatives and similar repositories for kron_torch:
Users that are interested in kron_torch are comparing it to the libraries listed below
- supporting pytorch FSDP for optimizers☆79Updated 3 months ago
- WIP☆93Updated 7 months ago
- Efficient optimizers☆183Updated last week
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆98Updated 2 months ago
- ☆169Updated 3 months ago
- 🧱 Modula software package☆173Updated last week
- ☆79Updated 11 months ago
- Focused on fast experimentation and simplicity☆69Updated 2 months ago
- ☆25Updated last year
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆135Updated last week
- ☆58Updated 4 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆100Updated 4 months ago
- ☆76Updated 8 months ago
- ☆47Updated 3 months ago
- DeMo: Decoupled Momentum Optimization☆182Updated 3 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆142Updated this week
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆73Updated 7 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆107Updated 3 months ago
- ☆52Updated 5 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆122Updated 11 months ago
- ☆33Updated 6 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆94Updated 7 months ago
- Scalable and Performant Data Loading☆230Updated this week
- ☆53Updated last year
- The AdEMAMix Optimizer: Better, Faster, Older.☆179Updated 6 months ago
- ☆149Updated 7 months ago
- ☆89Updated 2 months ago