EPISODE · Jul 28, 2026 · 10 MIN
AI 为什么这么贵?钱究竟烧在了哪里?
from 本利行间
大模型推理的账单,不只是“每个 token 多少钱”。参数要被搬运,计算要在 GPU 上执行,对话越长,KV cache 占用的显存越多;同时还要为并发、延迟目标和空闲容量付费。这一期从参数、GPU、内存带宽讲到 KV cache 与长上下文,把“AI 为什么贵”还原成一张由计算、内存、并发和服务质量共同决定的账单。时间戳:- 00:00 开场:AI 的钱烧在哪里- 01:19 参数不是知识卡片- 02:53 为什么偏偏是 GPU- 04:20 厨师算得快,资料也得送得上- 05:55 固定行李之外,还有越聊越大的随身包- 07:20 为什么长上下文不是免费午餐- 08:24 AI 成本不是单价乘 token 那么简单本节目只做阅读、思考和教育分享,不构成投资、医疗或其他专业建议。
Embed this episode
Ready to play
AI 为什么这么贵?钱究竟烧在了哪里?
0:00
10:22
1×
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
Frequently Asked Questions
How long is this episode of 本利行间?
This episode is 10 minutes long.
When was this 本利行间 episode published?
This episode was published on July 28, 2026.
Can I download this 本利行间 episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!