fal-ai-community / NativeSparseAttentionLinks
research impl of Native Sparse Attention (2502.11089)
☆60Updated 5 months ago
Alternatives and similar repositories for NativeSparseAttention
Users that are interested in NativeSparseAttention are comparing it to the libraries listed below
Sorting:
- ☆83Updated last year
- Focused on fast experimentation and simplicity☆76Updated 7 months ago
- supporting pytorch FSDP for optimizers☆84Updated 7 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆55Updated 4 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 11 months ago
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆65Updated last week
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- The evaluation framework for training-free sparse attention in LLMs☆86Updated last month
- ☆60Updated 4 months ago
- ☆21Updated 8 months ago
- H-Net Dynamic Hierarchical Architecture☆65Updated last week
- ☆19Updated 2 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆127Updated 8 months ago
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆42Updated 2 weeks ago
- Mixture of A Million Experts☆46Updated last year
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆244Updated 6 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆149Updated last month
- WIP☆93Updated 11 months ago
- RWKV-7: Surpassing GPT☆94Updated 8 months ago
- ☆34Updated 10 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- ☆114Updated last year
- ☆65Updated 8 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated 11 months ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆84Updated last year
- Accelerated First Order Parallel Associative Scan☆184Updated 11 months ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 3 months ago
- Here we will test various linear attention designs.☆62Updated last year
- ☆53Updated 10 months ago