{"slug":"llm-d","name":"llm-d","domain":null,"verdict":"As of 2026-08-10, ChatGPT, Claude, Gemini, Grok collectively rank llm-d #7 of 8 for open-source llm inference servers for kubernetes. Source: https://modelsagree.com/product/llm-d (modelsagree.com, CC BY 4.0).","best_rank":7,"categories":1,"entries":[{"slug":"best-open-source-llm-inference-servers-for-kubernetes","title":"Best open-source LLM inference servers for Kubernetes","rank":7,"of":8,"score":2,"appearances":1,"modelRanks":{"ChatGPT":4},"reason":"Best Kubernetes-native choice for large distributed LLM deployments, combining vLLM with inference-aware routing, disaggregated prefill/decode, KV-cache coordination, and Gateway API integration","reasons":[{"model":"ChatGPT","reason":"Best Kubernetes-native choice for large distributed LLM deployments, combining vLLM with inference-aware routing, disaggregated prefill/decode, KV-cache coordination, and Gateway API integration"}],"fixes":[{"model":"ChatGPT","fix":"It is still comparatively young and overengineered for teams serving a few models on one or two nodes"}],"updated":"2026-08-10","rank_history":{"days":["2026-08-03","2026-08-10"],"ranks":[7,null]},"api":"https://modelsagree.com/api/v1/best/best-open-source-llm-inference-servers-for-kubernetes.json"}],"page":"https://modelsagree.com/product/llm-d","check":"https://modelsagree.com/check?q=llm-d","updated":"2026-08-10T18:18:45.051Z","attribution":"modelsagree.com, CC BY 4.0"}