Before → After
基础版本已验证检查点
744.000B
744.000B
quantizationFP8
Quality retention target
Quality retention target
生产工件工件
谱系和基准报告
谱系和基准报告
GPU 定位
权重和 KV 缓存工程测量前的估算
Estimated VRAMMeasured and certified results are delivered with the project.
运行时打包transformers