zaydzuhri / softpick-attentionLinks
Implementations of attention with the softpick function, naive and FlashAttention-2
☆83Updated 3 months ago
Alternatives and similar repositories for softpick-attention
Users that are interested in softpick-attention are comparing it to the libraries listed below
Sorting:
- ☆85Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆90Updated 2 months ago
- ☆82Updated last year
- Normalized Transformer (nGPT)☆186Updated 9 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- ☆101Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆128Updated 8 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆152Updated last month
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- Token Omission Via Attention☆128Updated 10 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated last year
- Understand and test language model architectures on synthetic tasks.☆222Updated last month
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆84Updated last month
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- H-Net Dynamic Hierarchical Architecture☆77Updated last month
- ☆87Updated last year
- 📄Small Batch Size Training for Language Models☆42Updated 2 weeks ago
- ☆56Updated 10 months ago
- Mixture of A Million Experts☆46Updated last year
- research impl of Native Sparse Attention (2502.11089)☆60Updated 6 months ago
- Collection of autoregressive model implementation☆86Updated 4 months ago
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆65Updated 2 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆125Updated 8 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆131Updated last year
- ☆237Updated 2 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆69Updated 4 months ago
- ☆53Updated last year
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆81Updated 9 months ago