Function server_print_usage

examples/server/server.cpp:1751–1810

};

static void server_print_usage(const char *argv0, const gpt_params &params,
                               const server_params &sparams)
{
    printf("usage: %s [options]\n", argv0);
    printf("\n");
    printf("options:\n");
    printf("  -h, --help                show this help message and exit\n");
    printf("  -v, --verbose             verbose output (default: %s)\n", server_verbose ? "enabled" : "disabled");
    printf("  -t N, --threads N         number of threads to use during computation (default: %d)\n", params.n_threads);
    printf("  -tb N, --threads-batch N  number of threads to use during batch and prompt processing (default: same as --threads)\n");
    printf("  -c N, --ctx-size N        size of the prompt context (default: %d)\n", params.n_ctx);
    printf("  --rope-scaling {none,linear,yarn}\n");
    printf("                            RoPE frequency scaling method, defaults to linear unless specified by the model\n");
    printf("  --rope-freq-base N        RoPE base frequency (default: loaded from model)\n");
    printf("  --rope-freq-scale N       RoPE frequency scaling factor, expands context by a factor of 1/N\n");
    printf("  --yarn-ext-factor N       YaRN: extrapolation mix factor (default: 1.0, 0.0 = full interpolation)\n");
    printf("  --yarn-attn-factor N      YaRN: scale sqrt(t) or attention magnitude (default: 1.0)\n");
    printf("  --yarn-beta-slow N        YaRN: high correction dim or alpha (default: %.1f)\n", params.yarn_beta_slow);
    printf("  --yarn-beta-fast N        YaRN: low correction dim or beta (default: %.1f)\n", params.yarn_beta_fast);
    printf("  -b N, --batch-size N      batch size for prompt processing (default: %d)\n", params.n_batch);
    printf("  --memory-f32              use f32 instead of f16 for memory key+value (default: disabled)\n");
    printf("                            not recommended: doubles context memory required and no measurable increase in quality\n");
    if (llama_mlock_supported())
    {
        printf("  --mlock               force system to keep model in RAM rather than swapping or compressing\n");
    }
    if (llama_mmap_supported())
    {
        printf("  --no-mmap             do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
    }
    printf("  --numa                attempt optimizations that help on some NUMA systems\n");
#ifdef LLAMA_SUPPORTS_GPU_OFFLOAD
    printf("  -ngl N, --n-gpu-layers N\n");
    printf("                        number of layers to store in VRAM\n");
    printf("  -ts SPLIT --tensor-split SPLIT\n");
    printf("                        how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
    printf("  -mg i, --main-gpu i   the GPU to use for scratch and small tensors\n");
    printf("  -nommq, --no-mul-mat-q\n");
    printf("                        use cuBLAS instead of custom mul_mat_q CUDA kernels.\n");
    printf("                        Not recommended since this is both slower and uses more VRAM.\n");
#endif
    printf("  -m FNAME, --model FNAME\n");
    printf("                        model path (default: %s)\n", params.model.c_str());
    printf("  -a ALIAS, --alias ALIAS\n");
    printf("                        set an alias for the model, will be added as `model` field in completion response\n");
    printf("  --lora FNAME          apply LoRA adapter (implies --no-mmap)\n");
    printf("  --lora-base FNAME     optional model to use as a base for the layers modified by the LoRA adapter\n");
    printf("  --host                ip address to listen (default  (default: %s)\n", sparams.hostname.c_str());
    printf("  --port PORT           port to listen (default  (default: %d)\n", sparams.port);
    printf("  --path PUBLIC_PATH    path from which to serve static files (default %s)\n", sparams.public_path.c_str());
    printf("  -to N, --timeout N    server read/write timeout in seconds (default: %d)\n", sparams.read_timeout);
    printf("  --embedding           enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled");
    printf("  -np N, --parallel N   number of slots for process requests (default: %d)\n", params.n_parallel);
    printf("  -cb, --cont-batching  enable continuous batching (a.k.a dynamic batching) (default: disabled)\n");
    printf("    -spf FNAME, --system-prompt-file FNAME\n");
    printf("                        Set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications.\n");
    printf("  --vram-budget N       VRAM budget in GiB (default: -1, -1 = available VRAM)\n");
    printf("  --mmproj MMPROJ_FILE  path to a multimodal projector file for LLaVA.\n");