Jaykef / Triton-nanoGPT
Custom triton kernels for training Karpathy's nanoGPT.
☆18Updated 5 months ago
Alternatives and similar repositories for Triton-nanoGPT:
Users that are interested in Triton-nanoGPT are comparing it to the libraries listed below
- ☆76Updated 8 months ago
- Minimal but scalable implementation of large language models in JAX☆34Updated 4 months ago
- An implementation of the Llama architecture, to instruct and delight☆21Updated 2 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆100Updated 4 months ago
- ☆20Updated last year
- ☆51Updated 10 months ago
- Collection of autoregressive model implementation☆83Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆122Updated 11 months ago
- supporting pytorch FSDP for optimizers☆79Updated 3 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆71Updated 11 months ago
- ☆43Updated last year
- Experiment of using Tangent to autodiff triton☆78Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆58Updated last month
- ☆53Updated last year
- research impl of Native Sparse Attention (2502.11089)☆54Updated last month
- ☆74Updated 7 months ago
- ☆47Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated last week
- A MAD laboratory to improve AI architecture designs 🧪☆108Updated 3 months ago
- Triton Implementation of HyperAttention Algorithm☆47Updated last year
- A toolkit for scaling law research ⚖☆48Updated last month
- DPO, but faster 🚀☆40Updated 3 months ago
- ☆49Updated last year
- Learn CUDA with PyTorch☆19Updated last month
- ☆87Updated last week
- ☆52Updated 5 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆65Updated 7 months ago
- ☆95Updated 9 months ago
- ☆19Updated 5 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLore☆26Updated 6 months ago