fla-org / native-sparse-attentionLinks
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
☆778Updated 4 months ago
Alternatives and similar repositories for native-sparse-attention
Users that are interested in native-sparse-attention are comparing it to the libraries listed below
Sorting:
- Ring attention implementation with flash attention☆831Updated this week
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆700Updated last month
- Muon is Scalable for LLM Training☆1,240Updated this week
- TransMLA: Multi-Head Latent Attention Is All You Need☆335Updated 3 weeks ago
- slime is a LLM post-training framework aiming for RL Scaling.☆1,113Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆541Updated 3 weeks ago
- Scalable toolkit for efficient model reinforcement☆578Updated this week
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆428Updated 2 months ago
- Helpful tools and examples for working with flex-attention☆908Updated 3 weeks ago
- 🔥 A minimal training framework for scaling FLA models☆220Updated last month
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆399Updated last week
- Efficient LLM Inference over Long Sequences☆385Updated last month
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆483Updated 5 months ago
- Efficient triton implementation of Native Sparse Attention.☆186Updated 2 months ago
- LLM KV cache compression made easy☆566Updated last week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆183Updated last month
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆533Updated 2 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆331Updated last week
- ☆372Updated last week
- Muon is an optimizer for hidden layers in neural networks☆1,454Updated 3 weeks ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆456Updated this week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆307Updated 3 months ago
- Large Context Attention☆720Updated 6 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆221Updated last month
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆500Updated last week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆141Updated last week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,446Updated last week
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,055Updated 2 weeks ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆229Updated 3 weeks ago
- ☆802Updated last month