11 papers
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation
Wei-Rui Chen, Vignesh Kothapalli, Ata Fatahibaarzi +5
Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge disti…
Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction
Ryan Lucas, Kayhan Behdin, Zhipeng Wang +3
Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression t…
LLM Query Scheduling with Prefix Reuse and Latency Constraints
Gregory Dexter, Shao Tang, Ata Fatahi Baarzi +3
The efficient deployment of large language models (LLMs) in online settings requires optimizing inference performance under stringent latency constraints, particularly the time-to-…
Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems
Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song +17
Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Al…
Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures
Pingzhi Li, Morris Yu-Chao Huang, Zhen Tan +6
Knowledge Distillation (KD) accelerates training of large language models (LLMs) but poses intellectual property protection and LLM diversity risks. Existing KD detection methods b…
LANTERN: Scalable Distillation of Large Language Models for Job-Person Fit and Explanation
Zhoutong Fu, Yihan Cao, Yi-Lin Chen +16
Large language models (LLMs) have achieved strong performance across a wide range of natural language processing tasks. However, deploying LLMs at scale for domain specific applica…