6 papers
End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering
Jiliang Hu, Zuchao Li, Baoyuan Qi +2
Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processi…
Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
Luohe Shi, Zuchao Li, Lefei Zhang +3
Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typical…
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
Haoqi Yang, Yao Yao, Zuchao Li +3
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks. However, their extensive memory requirements, particularly…
DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression
Yi Zhao, Zuchao Li, Hai Zhao +2
Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-co…
KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding
Luohe Shi, Zuchao Li, Lefei Zhang +3
Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder archite…
SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers
Zicong Tang, Shi Luohe, Zuchao Li +4
Large Language Models (LLMs) have achieved impressive accomplishments in recent years. However, the increasing memory consumption of KV cache has possessed a significant challenge…