YouTube13 May 2026
26m

Token是如何定价的 | Reiner Pope | Roofline分析 | 计算瓶颈 | 内存瓶颈 | 单Token成本 | batch size | 稀疏度 | Scale-up | 内存过剩

Podcast cover

最佳拍档

Open in Podwise to generate AI notes

Sign in to process this episode and unlock summaries, transcripts, highlights and translations.

Open in Podwise

Shownotes are not generated by Podwise.

Token是如何定价的 | Reiner Pope | Roofline分析 | 计算瓶颈 | 内存瓶颈 | 单Token成本 | batch size | 稀疏度 | Scale-up | 内存过剩