Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
Paper
•
2307.15337
•
Published
•
36
Papers from the NICS-EFFALG Team
-
-
DiTFastAttn: Attention Compression for Diffusion Transformer Models
Paper • 2406.08552 • Published • 23 -
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Paper • 2406.02540 • Published • 2 -
Can LLMs Learn by Teaching? A Preliminary Study
Paper • 2406.14629 • Published • 19 -
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression
Paper • 2406.14909 • Published • 14 -
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Paper • 2405.17873 • Published • 2 -
Evaluating Quantized Large Language Models
Paper • 2402.18158 • Published -
A Survey on Efficient Inference for Large Language Models
Paper • 2404.14294 • Published • 2