CLAIRE-Labo / flash_attentionLinks
A basic pure pytorch implementation of flash attention
☆16Updated 9 months ago
Alternatives and similar repositories for flash_attention
Users that are interested in flash_attention are comparing it to the libraries listed below
Sorting:
- ☆83Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- Code for the paper "Function-Space Learning Rates"☆23Updated 2 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆81Updated 9 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- LL3M: Large Language and Multi-Modal Model in Jax☆72Updated last year
- 📄Small Batch Size Training for Language Models☆41Updated this week
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- ☆53Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆55Updated 4 months ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated 10 months ago
- Collection of autoregressive model implementation☆86Updated 3 months ago
- The evaluation framework for training-free sparse attention in LLMs☆88Updated last month
- WIP☆94Updated 11 months ago
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- ☆83Updated 11 months ago
- ☆39Updated 4 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆82Updated 3 weeks ago
- DPO, but faster 🚀☆44Updated 8 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated 11 months ago
- σ-GPT: A New Approach to Autoregressive Models☆67Updated 11 months ago
- ☆81Updated last year
- ☆31Updated 8 months ago
- ☆34Updated 10 months ago
- Jax like function transformation engine but micro, microjax☆33Updated 9 months ago
- Code for the paper "On the Expressivity Role of LayerNorm in Transformers' Attention" (Findings of ACL'2023)☆56Updated 10 months ago
- H-Net Dynamic Hierarchical Architecture☆65Updated 2 weeks ago
- ☆37Updated last year
- Experiment of using Tangent to autodiff triton☆80Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆149Updated last month