Skip to content

sglang 1

  • dsh-llm-sampling-params v0.2.1 Verified

    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).

    dsh plugin add dsh-llm-sampling-params