project
llama-server is the HTTP server component of llama.cpp, letting users run local LLM inference with configurable context, KV cache, and GPU settings.
No evidence-backed relationships are recorded.
llama-server b11430 reports logprob 0.0 for every speculatively decoded token, dragging one test's mean logprob from -0.48 to -0.0011. Nothing in the response or the server log flags the fill-ins, so evals and calibration built on those numbers go wrong quietly.
Reality
llama-server left the request hanging or crashed outright in all 73 trials where a 17,653-token prompt arrived 3 to 46 ms before its sleep timer fired. A one-token warm-up request sent first avoided both failures in 123 of 123 tries.
Reality
A quantised 27B on one 16GB GPU audited a home Splunk and Sysmon install with nothing leaving the host. Its first repair attempt ran the 128K context window dry. A halt rule in the system prompt got it under control.
Reality
A dev.to guide puts the llama.cpp and Ollama decision on ownership. Under Ollama the named model is the unit you operate; under llama.cpp it is the llama-server process and the seven flags in its command line.
Reality
Alibaba's new 27B model defaults reasoning_effort to xhigh. Simon Willison measured 22,276 reasoning tokens and 21 minutes for one SVG that took two minutes with reasoning off.
Reality