softmax1 / Flash-Attention-Softmax-NLinks
CUDA and Triton implementations of Flash Attention with SoftmaxN.
☆70Updated last year
Alternatives and similar repositories for Flash-Attention-Softmax-N
Users that are interested in Flash-Attention-Softmax-N are comparing it to the libraries listed below
Sorting:
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆62Updated 4 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆115Updated this week
- ☆108Updated last year
- ☆53Updated this week
- Make triton easier☆47Updated 11 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆75Updated last year
- ☆144Updated 2 years ago
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆66Updated 5 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 11 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆95Updated last year
- ☆78Updated 10 months ago
- Understand and test language model architectures on synthetic tasks.☆197Updated 2 months ago
- Experiment of using Tangent to autodiff triton☆79Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆75Updated 8 months ago
- Repository for CPU Kernel Generation for LLM Inference☆26Updated last year
- Load compute kernels from the Hub☆139Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆216Updated 6 months ago
- A toolkit for scaling law research ⚖☆49Updated 4 months ago
- QuIP quantization☆52Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Utilities for Training Very Large Models☆58Updated 8 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆132Updated 9 months ago
- Here we will test various linear attention designs.☆58Updated last year
- ☆50Updated 7 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLore☆28Updated 8 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆44Updated 10 months ago
- DPO, but faster 🚀☆42Updated 5 months ago