2 个仓库
Techniques for maximizing the number of workloads per physical node by reducing virtualization overhead.
Distinguishing note: Candidates focus on networking or monitoring, while this is about compute density and packing.
Explore 2 awesome GitHub repositories matching devops & infrastructure · Workload Density Optimization. Refine with filters or upvote what's useful.
KServe is an open platform for deploying and serving generative and predictive AI models on Kubernetes. It defines inference services as custom resources with declarative YAML specifications, enabling a Kubernetes-native approach to model deployment and lifecycle management. The platform leverages Knative-based serverless scaling for automatic scale-to-zero and revision management, and supports a pluggable serving runtime architecture that maps model formats to containerized execution environments. KServe distinguishes itself through model-aware autoscaling that scales replicas based on token
Adjusts GPU, memory, and autoscaling settings based on whether the workload is generative or predictive.
该项目提供了战略路线图和指南,详细介绍了托管容器编排和安全服务的演进与部署模式。它作为 EKS、ECS、ECR 和 Fargate 即将推出的功能和开发优先级的公共跟踪文档。 该资源包括云容器编排指南以及 Kubernetes 和 ECS 战略,概述了云基础设施的托管 Kubernetes 和专有编排服务的开发。它还提供了专注于扫描恶意活动和跟踪工作负载健康状况的安全和监控计划。 该材料涵盖了广泛的基础设施功能,包括资源配置、计算和任务的自动扩展以及容器镜像管理。它通过负载均衡和 Pod 密度优化来解决网络和流量管理问题,并通过日志路由和性能跟踪来解决可观测性问题。
Implements IPv4 prefix assignment to network interfaces to increase container density on Windows nodes.