llmaz is an open-source inference platform designed for deploying and managing large language models on Kubernetes. It supports multiple backends, distributed serving, and integrates with various model providers. The platform offers features like token-based rate limiting, model routing, and a built-in chatbot UI for rapid prototyping and production use.
Latest indexed changes and source events
inftyai.com discovered by the PulseGate indexer
Other apps tracked under the same category.
