#capacity
3 discoveries · Hand-picked discoveries from the open web, newest first.
-
Brooklyn’s Domino Park gets 750-capacity music venue
Brooklyn's Domino Park gets 750-capacity music venue The post Brooklyn’s Domino Park gets 750-capacity music venue appeared first on Paste Magazine .
Paste Music · EN
-
How to Plan LLM Inference Capacity for a Shared Platform
Published: 2026-07-29 A recurring capacity-planning request for an internal LLM platform is: We have selected a model. Do we have enough capacity, and how many GPUs would we need for N users? The question is missing the information needed to answer it. The model and its serving configuration determine the minimum resources required to start one replica. They don't tell us how many requests that replica can handle while meeting the product's latency and reliability requirements. That depends on prompt and response lengths, arrival rate, concurrency, cache reuse, calls per user task, traffic bur
Andrey Krisanov · EN
-
网络流笔记
最大流 概念 容量:$capacity(e)$ 表示一条有向边 $e(u, v)$ 的最大允许的流量。 流量:$flow(e)$ 表示一条有向边 $e(u, v)$ 总容量中已被占用的流量。 剩余流量(残量):$w(e) = c(e)-f(e)$,表示当前时刻某条有向边 $e(u, v)$ 总流量中未被占用的部分。 反向边:原图中每一条有向边在残量网络中都有对应的反向边,反向边的容量为 $0$,容量的变化与原边相反;『反向边』的概念是相对的,即一条边的反向边的反向边是它本身。 残量网络:在原图的基础之上,添加每条边对应的反向边,并储存每条边的当前流量。残量网络会在算法进行的过程中被修改。 增广路(augmenting path):残量网络中从源点到汇点的一条路径,增广路上所有边中最小的剩余容量为增广流量。 增广(augmenting):在残量网络中寻找一条增广路,并将增广路上所有边的流量加上增广流量的过程。 层次:$level(u)$ 表示节点 $u$ 在层次图中与源点的距离。 层次图:在原残量网络中按照每个节点的层次来分层,只保留相邻两层的节点的图,满载(即流量等于容量)的边不存在于层次图中。 流的三个重要性质: 容量限制:对于每条边,流经该边的流量不得超过该边的容量,即,$f(u,v)\leq c(u,v)$ 斜对称性:每条边的流量与其相反边的流量之和为 0,即 $f(u,v)
ChungZH 的小窝 · ZH