tilde-research / nsa-implLinks
An efficient implementation of the NSA (Native Sparse Attention) kernel
☆118Updated 3 months ago
Alternatives and similar repositories for nsa-impl
Users that are interested in nsa-impl are comparing it to the libraries listed below
Sorting:
- ☆129Updated 4 months ago
- The evaluation framework for training-free sparse attention in LLMs☆100Updated 3 months ago
- ☆89Updated 7 months ago
- ☆251Updated 4 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆189Updated 3 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆57Updated 3 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated 3 months ago
- ☆61Updated 3 months ago
- Fast and memory-efficient exact attention☆70Updated 7 months ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆40Updated last month
- Kinetics: Rethinking Test-Time Scaling Laws☆80Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆229Updated 4 months ago
- ☆96Updated 3 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆142Updated 4 months ago
- ☆143Updated 7 months ago
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated last year
- 🔥 A minimal training framework for scaling FLA models☆259Updated 3 weeks ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆79Updated last week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆234Updated 3 months ago
- ☆54Updated 3 months ago
- Fast and memory-efficient exact kmeans☆91Updated last week
- Transformers components but in Triton☆34Updated 5 months ago
- Work in progress.☆74Updated 3 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆77Updated last year
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆23Updated 7 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆49Updated 11 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆249Updated last week
- ☆14Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago