167 citations · 471 across the 83 of their papers we have counts for
Showing 2024 · cs.CLShow all
3 papers · 2 filters
cs.CL2024
Channel Merging: Preserving Specialization for Merged Experts
Mingyang Zhang, Jing Liu, Ganggui Ding +3
Lately, the practice of utilizing task-specific fine-tuning has been implemented to improve the performance of large language models (LLM) in subsequent tasks. Through the integrat…
cs.CL2024★ 1 cited
ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
Jing Liu, Ruihao Gong, Mingyang Zhang +3
LLM development involves pre-training a foundation model on massive data, followed by fine-tuning on task-specific data to create specialized experts. Serving these experts can pos…
cs.CL2024★ 3 cited
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Akide Liu, Jing Liu, Zizheng Pan +3
A critical approach for efficiently deploying computationally demanding large language models (LLMs) is Key-Value (KV) caching. The KV cache stores key-value states of previously g…