fal-ai-community / NativeSparseAttentionLinks
research impl of Native Sparse Attention (2502.11089)
☆60Updated 6 months ago
Alternatives and similar repositories for NativeSparseAttention
Users that are interested in NativeSparseAttention are comparing it to the libraries listed below
Sorting:
- Focused on fast experimentation and simplicity☆76Updated 8 months ago
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- ☆87Updated last year
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 5 months ago
- ☆34Updated 11 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- ☆65Updated 9 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…☆44Updated last month
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆69Updated last week
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆131Updated last year
- ☆19Updated 3 months ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 3 months ago
- Collection of autoregressive model implementation☆86Updated 4 months ago
- WIP☆94Updated last year
- ☆53Updated last year
- Normalized Transformer (nGPT)☆186Updated 9 months ago
- Experiment of using Tangent to autodiff triton☆80Updated last year
- ☆61Updated 5 months ago
- H-Net Dynamic Hierarchical Architecture☆77Updated last month
- ☆56Updated 10 months ago
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- ☆118Updated last year
- Accelerated First Order Parallel Associative Scan☆187Updated last year
- A library for unit scaling in PyTorch☆129Updated last month
- Mixture of A Million Experts☆46Updated last year
- ☆21Updated 9 months ago
- Here we will test various linear attention designs.☆62Updated last year