OOrhun Küpeli·Jul 21One GPU, Two LLMsBuilding a production-grade LLM inference platform on EKS with GPU time-slicing, KServe, Knative, and a custom gateway. Finally, debugging everything that broke.6 min read·orhunkupeli.hashnode.dev
OOrhun Küpeli·Jun 21The Numbers: Benchmarking My LLM Gateway on a H100Real H100 benchmark of a production LLM gateway vs a naive HuggingFace baseline continuous batching, streaming TTFT, graceful 429s.5 min read·orhunkupeli.hashnode.dev1
