srush / triton-autodiffLinks
Experiment of using Tangent to autodiff triton
☆80Updated last year
Alternatives and similar repositories for triton-autodiff
Users that are interested in triton-autodiff are comparing it to the libraries listed below
Sorting:
- ☆91Updated last year
- A library for unit scaling in PyTorch☆130Updated 3 months ago
- ☆121Updated last year
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆45Updated last year
- train with kittens!☆63Updated 11 months ago
- A place to store reusable transformer components of my own creation or found on the interwebs☆60Updated last week
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- JAX bindings for Flash Attention v2☆97Updated this week
- supporting pytorch FSDP for optimizers☆83Updated 10 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- ☆53Updated last year
- An implementation of the Llama architecture, to instruct and delight☆21Updated 4 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago
- Make triton easier☆48Updated last year
- Accelerated First Order Parallel Associative Scan☆189Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆131Updated 10 months ago
- ☆58Updated last year
- seqax = sequence modeling + JAX☆167Updated 3 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Updated 3 months ago
- PyTorch-native post-training at scale☆83Updated this week
- ☆21Updated 7 months ago
- This repository contains the experimental PyTorch native float8 training UX☆223Updated last year
- Automatically take good care of your preemptible TPUs☆37Updated 2 years ago
- ☆83Updated last year
- Personal solutions to the Triton Puzzles☆20Updated last year
- Implementation of Flash Attention in Jax☆219Updated last year
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year