18 citations · 111 across the 34 of their papers we have counts for
9 papers · 1 filter
Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
Jiayi Yuan, Hao Li, Xinheng Ding +7
Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are…
Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization
Yu-Neng Chuang, Leisheng Yu, Guanchu Wang +6
Large language models (LLMs) are increasingly deployed and democratized on edge devices. To improve the efficiency of on-device deployment, small language models (SLMs) are often a…
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
Jiayi Yuan, Hongyi Liu, Shaochen Zhong +9
Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts. This capability enables complex task-…
Learning to Compress Prompt in Natural Language Formats
Yu-Neng Chuang, Tianwei Xing, Chia-Yuan Chang +3
Large language models (LLMs) are great at processing multiple natural language processing tasks, but their abilities are constrained by inferior performance with long context, slow…
Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
Zihao Li, Yucheng Shi, Zirui Liu +4
The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing s…
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Zirui Liu, Jiayi Yuan, Hongye Jin +5
Efficiently serving large language models (LLMs) requires batching of many requests to reduce the cost per request. Yet, with larger batch sizes and longer context lengths, the key…
FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference
Zirui Liu, Qingquan Song, Qiang Charles Xiao +4
The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity har…
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
Hongye Jin, Xiaotian Han, Jingfeng Yang +5
It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for process…
Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt
Zhaozhuo Xu, Zirui Liu, Beidi Chen +5
While the numerous parameters in Large Language Models (LLMs) contribute to their superior performance, this massive scale makes them inefficient and memory-hungry. Thus, they are…