dhcode-cpp / NSA-pytorchLinks
DeepSeek Native Sparse Attention pytorch implementation
☆70Updated 3 months ago
Alternatives and similar repositories for NSA-pytorch
Users that are interested in NSA-pytorch are comparing it to the libraries listed below
Sorting:
- qwen-nsa☆66Updated last month
- Efficient triton implementation of Native Sparse Attention.☆155Updated last week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆102Updated this week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆107Updated 2 weeks ago
- TransMLA: Multi-Head Latent Attention Is All You Need☆284Updated this week
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆158Updated 3 weeks ago
- ☆131Updated last month
- A sparse attention kernel supporting mix sparse patterns☆219Updated 3 months ago
- ☆93Updated 2 weeks ago
- The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆129Updated last week
- Efficient Mixture of Experts for LLM Paper List☆68Updated 5 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆166Updated last week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆203Updated 2 weeks ago
- 🔥 A minimal training framework for scaling FLA models☆146Updated 3 weeks ago
- [ICML 2025] Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆70Updated this week
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆114Updated last year
- ☆188Updated last month
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆294Updated 3 months ago
- analyse problems of AI with Math and Code☆16Updated this week
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆76Updated 4 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆83Updated last month
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated 10 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆46Updated 6 months ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆74Updated 5 months ago
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆94Updated this week
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆107Updated 7 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated 11 months ago
- [ICML 2025 Spotlight] Mixture of Lookup Experts☆24Updated 3 weeks ago
- ☆138Updated 3 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 10 months ago