Li, W., Zhang, Y., Luo, G., Wan, H., Gong, Z., Chao, F., & Ji, R. (2025). Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval.
Cita Chicago Style (17a ed.)Li, Wenhao, Yuxin Zhang, Gen Luo, Haiyuan Wan, Ziyang Gong, Fei Chao, y Rongrong Ji. Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval. 2025.
Cita MLA (9a ed.)Li, Wenhao, et al. Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval. 2025.
Precaución: Estas citas no son 100% exactas.