Meta tags:
description=;

Headings (most frequently used words):

mosec, highly, performant, ease, of, use, dynamic, batching, pipelined, stages, do, one, thing, well, cloud, friendly,

Text of the page (most frequently used words):
the (6), and (4), cloud (3), model (3), users (3), for (3), mosec (3), powered (2), with (2), serving (2), can (2), pipelined (2), #stages (2), cpu (2), which (2), efficient (2), github (2), contributing, zola, deigned, run, warmup, graceful, shutdown, prometheus, monitoring, metrics, easily, managed, kubernetes, any, container, orchestration, systems, friendly, focus, online, part, pay, attention, performance, business, logic, one, thing, well, spawn, multiple, processes, handle, gpu, mixed, workloads, aggregate, requests, from, different, batched, inference, distribute, results, back, dynamic, batching, user, interface, purely, python, serve, their, models, framework, agnostic, manner, using, same, code, they, offline, testing, ease, use, web, layer, task, coordination, built, rust, offers, blazing, speed, addition, utilization, async, highly, performant, apache, license, get, started, made, docs,

Text of the page (random words):
mosec mosec github docs mosec model serving made efficient in the cloud get started apache 2 0 license github highly performant web layer and task coordination built with rust which offers blazing speed in addition to efficient cpu utilization powered by async i o ease of use user interface purely in python by which users can serve their models in an ml framework agnostic manner using the same code as they do for offline testing dynamic batching aggregate requests from different users for batched inference and distribute results back pipelined stages spawn multiple processes for pipelined stages to handle cpu gpu io mixed workloads do one thing well focus on the online serving part users can pay attention to the model performance and business logic cloud friendly deigned to run in the cloud with the model warmup graceful shutdown and prometheus monitoring metrics easily managed by kubernetes or any container orchestration systems powered by zola contributing