Gojek Integrations

Kubernetes is a highly scalable platform for model inference that uses standards-based models. Trusted AI. KServe, a Kubernetes standard model inference platform, is designed for highly scalable applications. Provides a standardized, performant inference protocol that works across all ML frameworks. Modern serverless inference workloads supported by autoscaling, including a scale up to zero on GPU. High scalability, density packing, intelligent routing with ModelMesh. Production ML serving is simple and pluggable. Pre/post-processing, monitoring and explainability are all possible. Advanced deployments using the canary rollout, experiments and ensembles as well as transformers. ModelMesh was designed for high-scale, high density, and often-changing model use cases. ModelMesh intelligently loads, unloads and transfers AI models to and fro memory. This allows for a smart trade-off between user responsiveness and computational footprint.

One platform that combines modular, customizable, scalable, and modular map data management, SDKs, and APIs. NextBillion.ai's Mapverse is a cloud-agnostic platform for global-scale map data management. You can integrate any third-party data such as OSM, HERE, and TomTom and also leverage your own internal data. You can add custom map data layers to your data. You can route, geocode, navigate to it, and serve them in map tile form. Maps, routing, and places APIs + SDKs can be customized to your fleet type, geography, and use case. Optimize search and geocoding and use actual delivery locations in your apps instead of rooftop geocodes. Keep detailed maps of apartment buildings, gated communities and parking lots. Optimize the last leg to maximize delivery efficiency and customer satisfaction.