deep-spin / adasplashLinks
AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)
☆32Updated 4 months ago
Alternatives and similar repositories for adasplash
Users that are interested in adasplash are comparing it to the libraries listed below
Sorting:
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆56Updated last year
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 months ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆28Updated 5 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆86Updated 6 months ago
- ☆27Updated 2 months ago
- Official Implementation of FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration☆29Updated 2 months ago
- ☆16Updated 2 years ago
- [NeurIPS '25] Multi-Token Prediction Needs Registers☆26Updated last month
- The evaluation framework for training-free sparse attention in LLMs☆117Updated last week
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆20Updated 7 months ago
- ☆36Updated 10 months ago
- ☆31Updated last year
- ☆39Updated last year
- Beyond KV Caching: Shared Attention for Efficient LLMs☆20Updated last year
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆70Updated 7 months ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆29Updated 6 months ago
- [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…☆67Updated last year
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining (NeurIPS 2024)☆39Updated last year
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆98Updated last year
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆29Updated 11 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆88Updated last year
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆23Updated 2 months ago
- [EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs☆15Updated last year
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆73Updated 6 months ago
- ☆30Updated last year
- ☆11Updated last year
- ☆25Updated last year
- ☆63Updated 2 years ago
- ☆64Updated 6 months ago