ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
Paper
•
2402.15220
•
Published
•
23
base
-
-
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 111 -
MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection
Paper • 2403.19888 • Published • 12 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 106 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 99 -
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model
Paper • 2404.09967 • Published • 22 -
Multi-Head Mixture-of-Experts
Paper • 2404.15045 • Published • 61 -
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Paper • 2405.21060 • Published • 68