Comparison of KV-Cache Quantization (KVQ) Models
收藏DataCite Commons2025-06-29 更新2026-05-04 收录
下载链接：
https://orkg.org/comparison/R1410880
下载链接
链接失效反馈官方服务：
资源简介：
KV- Cache Quantization helps optimize memory usage in large language models, particularly as the number of input tokens grows. This comparison explored 6 KV-Cache Quantization (KVQ) Models and compared their specific characteristics such as main LLMs, bit widths, perplexity differences.
提供机构：
Open Research Knowledge Graph
创建时间：
2025-06-29
