https://blog.regmi.dev Personal Blog about anything that occurs to me en Mon, 25 May 2026 12:57:14 +0000 © 2026 Bijay's Blog https://blog.regmi.dev/post/understanding-llms-and-modern-inference-engines Choosing an LLM inference engine is a hardware-and-systems decision, not a meme. For real self-hosting, runtime, throughput, concurrency, and cost matter as much as the model. https://blog.regmi.dev/post/understanding-llms-and-modern-inference-engines Mon, 25 May 2026 12:57:14 +0000 bijay@regmi.dev bijayregmi llms inference inference-engines vllm llama-cpp tensorrt-llm sglang self-hosting open-source-models gpu nvidia ai-infrastructure https://blog.regmi.dev/post/state-of-naive-rag-vs-agentic-rag-in-2026 RAG is not dead. In 2026, agentic RAG often beats naïve RAG for accuracy and complex retrieval, but naïve RAG still wins for simple, fast, low-cost use cases. https://blog.regmi.dev/post/state-of-naive-rag-vs-agentic-rag-in-2026 Sun, 17 May 2026 09:59:59 +0000 bijay@regmi.dev bijayregmi rag data_engineering ai_engineering en english https://blog.regmi.dev/post/ein-medizinisches-modell-mit-synthetischen-daten Optimierte KI-Modelle für die medizinische Kodierung: Wie BERT und synthetische Daten den Klinikalltag revolutionieren. https://blog.regmi.dev/post/ein-medizinisches-modell-mit-synthetischen-daten Sun, 17 May 2026 09:59:59 +0000 bijay@regmi.dev bijayregmi medizin ki ai de german