awesome-repositories.com
博客
MCP
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目MCP 服务器关于排名机制媒体报道
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

3 个仓库

Awesome GitHub RepositoriesInference Routing Protocols

Specifies a content-level classification and semantic routing framework for AI inference systems as an IETF protocol.

Distinct from Routing Protocols: No candidate covers an IETF protocol specification for AI inference routing; closest are network routing protocols.

Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Inference Routing Protocols. Refine with filters or upvote what's useful.

Awesome Inference Routing Protocols GitHub Repositories

用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
  • kserve/kservekserve 的头像

    kserve/kserve

    5,576在 GitHub 上查看↗

    KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference services. It supports both generative AI models, including large language models, and traditional predictive models from frameworks such as TensorFlow, PyTorch, Scikit-Learn, XGBoost, and ONNX. The platform manages the full lifecycle of model deployments, including revision tracking, canary rollouts, A/B testing, and automatic rollbacks, and provides serverless scale-to-zero capabilities for cost-efficient resource management. KServe distinguishes itself through a standardized infere

    Standardizes inference requests and responses across REST and gRPC with health checking and metadata endpoints.

    Go
    在 GitHub 上查看↗5,576
  • seldonio/seldon-coreSeldonIO 的头像

    SeldonIO/seldon-core

    4,752在 GitHub 上查看↗

    Seldon Core 是一个基于 Kubernetes 的机器学习模型服务器和 MLOps 推理框架。它作为多模型服务引擎和流水线编排器,将模型打包为可通过标准化 REST 和 gRPC API 暴露的可扩展微服务。 该项目的独特之处在于基于图的推理流水线,可将模型和数据转换器链接成顺序工作流。它通过多模型共享服务和动态内存超额分配策略优化硬件利用率,同时通过加权流量路由、A/B 测试和影子部署支持生产环境实验。 该框架涵盖了广泛的 MLOps 功能,包括基于需求的自动扩缩容、通过消息总线进行的异步请求处理,以及针对数据漂移、异常值和预测可解释性的全面监控。它还提供用于模型运行时配置的基础设施管理,以及跨控制平面和数据平面的 TLS 加密安全通信。

    Implements standardized REST and gRPC protocols for consistent request and response handling across different model runtimes.

    Goaiopsdeploymentkubernetes
    在 GitHub 上查看↗4,752
  • vllm-project/semantic-routervllm-project 的头像

    vllm-project/semantic-router

    3,205在 GitHub 上查看↗

    Specifies a content-level classification and semantic routing framework as an IETF protocol.

    Goai-gatewaybert-classificationfine-tuning
    在 GitHub 上查看↗3,205
  1. Home
  2. Artificial Intelligence & ML
  3. Inference Routing Protocols

探索子标签

  • Standardized Inference ProtocolsStandardizes inference requests and responses across REST and gRPC with health checking and metadata endpoints. **Distinct from Inference Routing Protocols:** Distinct from Inference Routing Protocols: focuses on the protocol specification itself, not routing frameworks.
  • Standardized V2 ProtocolsStandardized V2 inference protocol supporting REST and gRPC, health checking, and rich metadata. **Distinct from Inference Routing Protocols:** Distinct from Inference Routing Protocols: focuses on the standardized V2 protocol specification, not routing frameworks.