qiuzh20 / gated_attentionLinks
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
☆95Updated last month
Alternatives and similar repositories for gated_attention
Users that are interested in gated_attention are comparing it to the libraries listed below
Sorting:
- ☆104Updated last month
- ☆61Updated 3 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆103Updated 2 weeks ago
- Long Context Extension and Generalization in LLMs☆62Updated last year
- ☆25Updated 2 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆65Updated 3 months ago
- ☆44Updated 3 weeks ago
- ☆119Updated 4 months ago
- Stick-breaking attention☆61Updated 3 months ago
- [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆88Updated last year
- ☆98Updated last month
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆39Updated last year
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆69Updated 3 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆131Updated 3 months ago
- "Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding" Zhenyu Zhang, Runjin Chen, Shiw…☆30Updated last year
- Kinetics: Rethinking Test-Time Scaling Laws☆81Updated 3 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆52Updated 11 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆38Updated last year
- Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"☆46Updated 2 months ago
- Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]☆35Updated last year
- ☆33Updated last year
- ☆19Updated 9 months ago
- ☆55Updated 4 months ago
- Code for paper "Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning"☆83Updated last year
- Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"☆28Updated last year
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆58Updated 2 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆121Updated 6 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆49Updated last year
- ☆18Updated 10 months ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆97Updated 10 months ago