4 papers
ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling
Yuchen Yang, Yaru Zhao, Pu Yang +2
While Mixture-of-Experts (MoE) architectures substantially bolster the expressive power of large-language models, their prohibitive memory footprint severely impedes the practical…
When Elo Lies: Hidden Biases in Codeforces-Based Evaluation of Large Language Models
Shenyu Zheng, Ximing Dong, Xiaoshuang Liu +6
As Large Language Models (LLMs) achieve breakthroughs in complex reasoning, Codeforces-based Elo ratings have emerged as a prominent metric for evaluating competitive programming c…
Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
Ximing Dong, Shaowei Wang, Dayi Lin +2
Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large R…
Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization
Ximing Dong, Shaowei Wang, Dayi Lin +1
Optimizing Large Language Model (LLM) performance requires well-crafted prompts, but manual prompt engineering is labor-intensive and often ineffective. Automated prompt optimizati…