Local GGUF inference for .NET — design notes, architecture, and release updates.https://llmdot.cognisoc.com/en-ushttps://llmdot.cognisoc.com/blog/managed-by-default-and-the-cpu-path/https://llmdot.cognisoc.com/blog/managed-by-default-and-the-cpu-path/Most .NET inference stories start with a GPU and treat CPU as the leftover. llmdot starts the other way around — and the resulting deployment story is the actual product advantage.Wed, 06 May 2026 00:00:00 GMThttps://llmdot.cognisoc.com/blog/four-execution-templates/https://llmdot.cognisoc.com/blog/four-execution-templates/How a small config-driven design collapses the modern decoder zoo into four execution templates — and why that matters for a .NET runtime that wants to stay small.Wed, 22 Apr 2026 00:00:00 GMThttps://llmdot.cognisoc.com/blog/why-gguf-native-for-dotnet/https://llmdot.cognisoc.com/blog/why-gguf-native-for-dotnet/GGUF is what the open model community actually publishes. For a .NET inference runtime, picking it as the primary format eliminates a class of problems before code is written.Wed, 08 Apr 2026 00:00:00 GMT