2 papers
cs.CL2025
DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
Yunhai Hu, Tianhua Xia, Zining Liu +6
Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language mode…
cs.CL2025
Rethinking the Outlier Distribution in Large Language Models: An In-depth Study
Rahul Raman, Khushi Sharma, Sai Qian Zhang
Investigating outliers in large language models (LLMs) is crucial due to their significant impact on various aspects of LLM performance, including quantization and compression. Out…