SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

arXiv:2402.09025v1 Announce Type: cross
Abstract: Large language models (LLMs) have proven to be highly effective across various natural language processing tasks. However, their large number of parameters poses significant challenges for practical deployment. Pruning, a technique aimed at reducing the size and complexity of LLMs, offers a potential solution by removing redundant components from the network. Despite the promise of pruning, existing methods often struggle to achieve substantial end-to-end LLM inference speedup. In this paper, we introduce SLEB, a novel …

arxiv cs.cl cs.lg llms redundancy through transformer type verification