PiotrNawrot / nano-sparse-attentionLinks
The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
☆62Updated 4 months ago
Alternatives and similar repositories for nano-sparse-attention
Users that are interested in nano-sparse-attention are comparing it to the libraries listed below
Sorting:
- Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"☆32Updated last month
- 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
- Fast and memory-efficient exact attention☆68Updated 2 months ago
- ☆53Updated this week
- ☆81Updated last year
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆126Updated 5 months ago
- ☆74Updated 3 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆126Updated 3 weeks 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
- ☆108Updated last year
- Experiment of using Tangent to autodiff triton☆78Updated last year
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆70Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆73Updated 7 months ago
- ☆45Updated 3 months ago
- ☆52Updated last year
- ☆129Updated 3 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆115Updated this week
- Load compute kernels from the Hub☆139Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆216Updated 6 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆67Updated 10 months ago
- ☆50Updated 7 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆149Updated last month
- Cascade Speculative Drafting☆29Updated last year
- ☆92Updated 8 months ago
- Understand and test language model architectures on synthetic tasks.☆195Updated 2 months ago
- Here we will test various linear attention designs.☆58Updated last year
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆47Updated last month