# Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity

> Research article (Proceedings of the VLDB Endowment, 2023) · cited 39× · AI/ML

**Wikidata**: [openalex:W4389576338](https://www.wikidata.org/wiki/openalex:W4389576338)  
**Source**: https://4ort.xyz/entity/flash-llm-enabling-cost-effective-and-highly-efficient-large-generative-model-inference-with-unstructured-sparsity