7 papers
Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis
Zehua Pei, Hui-Ling Zhen, Lancheng Zou +5
Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consuming the majority of computational res…
KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
Xing Li, Zeyu Xing, Yiming Li +6
KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness.…
AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
Qingyue Yang, Jie Wang, Xing Li +8
With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context…
Faster and Better LLMs via Latency-Aware Test-Time Scaling
Zili Wang, Tianyu Zhang, Haoli Bai +5
Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency…
FlatQuant: Flatness Matters for LLM Quantization
Yuxuan Sun, Ruikang Liu, Haoli Bai +10
Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and…
TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
Weizhe Lin, Xing Li, Zhiyuan Yang +7
Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning…