Function print_model_runtime

ds4_help.c:146–186

}

static void print_model_runtime(FILE *fp, const help_colors *c,
                                ds4_help_tool tool, bool full) {
    title(fp, c, "Model And Runtime");
    opt(fp, c, "-m, --model FILE", "GGUF model path. Default: ds4flash.gguf");
    if (tool == DS4_HELP_DS4 || tool == DS4_HELP_AGENT || tool == DS4_HELP_SERVER) {
        opt(fp, c, "--vision FILE", "Vision encoder GGUF for the selected model.");
    }
#ifdef DS4_ROCM_BUILD
    opt(fp, c, "--metal | --rocm | --cpu", "Select the backend explicitly.");
    opt(fp, c, "--backend NAME", "Backend name: metal, rocm, or cpu.");
#else
    opt(fp, c, "--metal | --cuda | --cpu", "Select the backend explicitly.");
    opt(fp, c, "--backend NAME", "Backend name: metal, cuda, or cpu.");
    opt(fp, c, "--gpu-vram N[,N,...]|auto", "CUDA VRAM budgets per device, in GiB, or auto-detect free VRAM.");
    opt(fp, c, "--gpu-devices N[,N,...]", "CUDA device indices used by multi-GPU placement.");
    if (tool != DS4_HELP_EVAL) {
        opt(fp, c, "--cuda-tensor-parallel", "Enable the paired DeepSeek tensor/expert path on an even multi-GPU CUDA placement.");
    }
#endif
    if (tool != DS4_HELP_BENCH) {
        opt(fp, c, "-c, --ctx N", "Allocated context tokens.");
    }
    if (tool == DS4_HELP_SERVER) {
        opt(fp, c, "-n, --tokens N", "Default max output tokens when clients omit a limit.");
    }
    opt(fp, c, "-t, --threads N", "CPU helper threads for host-side/reference work.");
    opt(fp, c, "--power N", "GPU duty-cycle target, 1..100. Default: 100");
    opt(fp, c, "--ssd-streaming", "Metal/CUDA/ROCm: opt in to SSD-backed model streaming instead of full residency.");
    opt(fp, c, "--ssd-streaming-cold", "SSD streaming: skip default popularity-based expert-cache preload.");
    opt(fp, c, "--ssd-streaming-cache-experts N|NGB", "SSD streaming cache target. N requests dynamic expert slots; NGB also reserves two full prefill layers. Either may be reduced to fit the model, graph, context, and backend working set.");
    opt(fp, c, "--ssd-streaming-full-layers N", "GLM Metal streaming: keep the first N routed layers fully resident. Default: auto from NGB expert budget; use 0 to disable.");
    opt(fp, c, "--ssd-streaming-preload-experts N", "SSD streaming: upfront popularity preload count. DeepSeek auto-seeds by default; GLM demand-fills unless N is explicit.");
    opt(fp, c, "--simulate-used-memory NGB", "Diagnostic: lock N GiB before model load to simulate a smaller-memory machine.");
    opt(fp, c, "--prefill-chunk N", "Graph prefill chunk size. Default: CUDA TP 2048; PRO long prompts 8192; others 4096.");
    if (full) {
        if (tool == DS4_HELP_EVAL || tool == DS4_HELP_BENCH) {
            opt(fp, c, "--mtp-model FILE", "External MTP or DSpark support GGUF.");
        }
        if (tool == DS4_HELP_DS4 || tool == DS4_HELP_AGENT || tool == DS4_HELP_SERVER) {
            opt(fp, c, "--mtp", "Enable model-embedded MTP speculation.");
            opt(fp, c, "--mtp-model FILE", "External MTP or DSpark support GGUF.");
            opt(fp, c, "--mtp-draft N", "Maximum autoregressive MTP draft tokens. Default: 1");
            opt(fp, c, "--mtp-margin F", "Verifier confidence margin for fast MTP acceptance. Default: 3");
            opt(fp, c, "--mtp-timing", "Enable embedded MTP and print acceptance/timing counters.");