llama-server 3

DSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to a local llama.cpp / llama-server gateway.

dsh addon: a Local Models settings tab that starts and stops a llama-server child process living with the dsh host process.

DSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty/repetition_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to an OpenAI-compatible gateway (llama.cpp, SGLang, vLLM).