thib-s / flash-newton-schulzLinks
My attempt to improve the speed of the newton schulz algorithm, starting from the dion implementation.
☆22Updated last week
Alternatives and similar repositories for flash-newton-schulz
Users that are interested in flash-newton-schulz are comparing it to the libraries listed below
Sorting:
- Quantized Attention on GPU☆44Updated last year
- flex-block-attn: an efficient block sparse attention computation library☆91Updated 2 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- ☆32Updated last year
- ☆100Updated 9 months ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated last year
- ☆132Updated 6 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆126Updated 5 months ago
- Fast and memory-efficient exact kmeans☆130Updated last month
- Triton implement of bi-directional (non-causal) linear attention☆57Updated 10 months ago
- ☆114Updated 6 months ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆29Updated 3 months ago
- ☆203Updated 3 weeks ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated last week
- ☆23Updated 7 months ago
- ☆47Updated last month
- Transformers components but in Triton☆34Updated 7 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆93Updated 10 months ago
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆45Updated 3 months ago
- The evaluation framework for training-free sparse attention in LLMs☆106Updated 2 months ago
- ☆52Updated 6 months ago
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆27Updated 3 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- ☆124Updated 3 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆223Updated 5 months ago
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆27Updated this week
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Updated 2 years ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆134Updated last month
- ☆58Updated 2 years ago