// UI configs

bool ui = true;

bool ui_mcp_proxy = false;

std::string ui_config_json;

| `-mmu, --mmproj-url URL` | URL to a multimodal projector file. see tools/mtmd/README.md<br/>(env: LLAMA_ARG_MMPROJ_URL) |

| `--mmproj-auto, --no-mmproj, --no-mmproj-auto` | whether to use multimodal projector file (if available), useful when using -hf (default: enabled)<br/>(env: LLAMA_ARG_MMPROJ_AUTO) |

| `--mmproj-offload, --no-mmproj-offload` | whether to enable GPU offloading for multimodal projector (default: enabled)<br/>(env: LLAMA_ARG_MMPROJ_OFFLOAD) |

| `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MIN_TOKENS) |

| `--image-max-tokens N` | maximum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MAX_TOKENS) |

| `--chat-template-kwargs STRING` | sets additional params for the json template parser, must be a valid json object string, e.g. '{"key1":"value1","key2":"value2"}'<br/>(env: LLAMA_ARG_CHAT_TEMPLATE_KWARGS) |

| `--chat-template-file JINJA_TEMPLATE_FILE` | set custom jinja chat template file (default: template taken from model's metadata)<br/>if suffix/prefix are specified, template will be disabled<br/>only commonly used templates are accepted (unless --jinja is set before this flag):<br/>list of built-in templates:<br/>bailing, bailing-think, bailing2, chatglm3, chatglm4, chatml, command-r, deepseek, deepseek-ocr, deepseek2, deepseek3, exaone-moe, exaone3, exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, granite-4.0, granite-4.1, grok-2, hunyuan-dense, hunyuan-moe, hunyuan-vl, kimi-k2, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, mistral-v7-tekken, monarch, openchat, orion, pangu-embedded, phi3, phi4, rwkv-world, seed_oss, smolvlm, solar-open, vicuna, vicuna-orca, yandex, zephyr<br/>(env: LLAMA_ARG_CHAT_TEMPLATE_FILE) |

| `--skip-chat-parsing, --no-skip-chat-parsing` | force a pure content parser, even if a Jinja template is specified; model will output everything in the content section, including any reasoning and/or tool calls (default: disabled)<br/>(env: LLAMA_ARG_SKIP_CHAT_PARSING) |

| `--simple-io` | use basic IO for better compatibility in subprocesses and limited consoles |

| `--spec-draft-hf, -hfd, -hfrd, --hf-repo-draft <user>/<model>[:quant]` | Same as --hf-repo, but for the draft model (default: unused)<br/>(env: LLAMA_ARG_SPEC_DRAFT_HF_REPO) |

| `--spec-draft-threads, -td, --threads-draft N` | number of threads to use during generation (default: same as --threads) |

| `--spec-draft-threads-batch, -tbd, --threads-batch-draft N` | number of threads to use during batch and prompt processing (default: same as --threads-draft) |

| `-np, --parallel N` | number of server slots (default: -1, -1 = auto)<br/>(env: LLAMA_ARG_N_PARALLEL) |

| `-cb, --cont-batching, -nocb, --no-cont-batching` | whether to enable continuous batching (a.k.a dynamic batching) (default: enabled)<br/>(env: LLAMA_ARG_CONT_BATCHING) |

| `-mm, --mmproj FILE` | path to a multimodal projector file. see tools/mtmd/README.md<br/>note: if -hf is used, this argument can be omitted<br/>(env: LLAMA_ARG_MMPROJ) |

| `-mmu, --mmproj-url URL` | URL to a multimodal projector file. see tools/mtmd/README.md<br/>(env: LLAMA_ARG_MMPROJ_URL) |

| `--mmproj-auto, --no-mmproj, --no-mmproj-auto` | whether to use multimodal projector file (if available), useful when using -hf (default: enabled)<br/>(env: LLAMA_ARG_MMPROJ_AUTO) |

| `--mmproj-offload, --no-mmproj-offload` | whether to enable GPU offloading for multimodal projector (default: enabled)<br/>(env: LLAMA_ARG_MMPROJ_OFFLOAD) |

| `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MIN_TOKENS) |

| `--image-max-tokens N` | maximum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MAX_TOKENS) |

| `-a, --alias STRING` | set model name aliases, comma-separated (to be used by API)<br/>(env: LLAMA_ARG_ALIAS) |

| `--tags STRING` | set model tags, comma-separated (informational, not used for routing)<br/>(env: LLAMA_ARG_TAGS) |

| `--embd-normalize N` | normalisation for embeddings (default: 2) (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm) |

| `--reuse-port` | allow multiple sockets to bind to the same port (default: disabled)<br/>(env: LLAMA_ARG_REUSE_PORT) |

| `--path PATH` | path to serve static files from (default: )<br/>(env: LLAMA_ARG_STATIC_PATH) |

| `--api-prefix PREFIX` | prefix path the server serves from, without the trailing slash (default: )<br/>(env: LLAMA_ARG_API_PREFIX) |

| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)<br/>specify "all" to enable all tools<br/>available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, apply_diff, get_datetime<br/>(env: LLAMA_ARG_TOOLS) |

| `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)<br/>(env: LLAMA_ARG_EMBEDDINGS) |

| `--rerank, --reranking` | enable reranking endpoint on server (default: disabled)<br/>(env: LLAMA_ARG_RERANKING) |

| `--api-key KEY` | API key to use for authentication, multiple keys can be provided as a comma-separated list (default: none)<br/>(env: LLAMA_API_KEY) |

| `--ssl-cert-file FNAME` | path to file a PEM-encoded SSL certificate<br/>(env: LLAMA_ARG_SSL_CERT_FILE) |

| `--chat-template-kwargs STRING` | sets additional params for the json template parser, must be a valid json object string, e.g. '{"key1":"value1","key2":"value2"}'<br/>(env: LLAMA_ARG_CHAT_TEMPLATE_KWARGS) |

| `-to, --timeout N` | server read/write timeout in seconds (default: 3600)<br/>(env: LLAMA_ARG_TIMEOUT) |

| `--threads-http N` | number of threads used to process HTTP requests (default: -1)<br/>(env: LLAMA_ARG_THREADS_HTTP) |

| `--cache-prompt, --no-cache-prompt` | whether to enable prompt caching (default: enabled)<br/>(env: LLAMA_ARG_CACHE_PROMPT) |

| `--cache-reuse N` | min chunk size to attempt reusing from the cache via KV shifting, requires prompt caching to be enabled (default: 0)<br/>[(card)](https://ggml.ai/f0.png)<br/>(env: LLAMA_ARG_CACHE_REUSE) |

| `-sps, --slot-prompt-similarity SIMILARITY` | how much the prompt of a request must match the prompt of a slot in order to use that slot (default: 0.10, 0.0 = disabled) |

| `--lora-init-without-apply` | load LoRA adapters without applying them (apply later via POST /lora-adapters) (default: disabled) |

| `--sleep-idle-seconds SECONDS` | number of seconds of idleness after which the server will sleep (default: -1; -1 = disabled) |

| `--spec-draft-hf, -hfd, -hfrd, --hf-repo-draft <user>/<model>[:quant]` | Same as --hf-repo, but for the draft model (default: unused)<br/>(env: LLAMA_ARG_SPEC_DRAFT_HF_REPO) |

| `--spec-draft-threads, -td, --threads-draft N` | number of threads to use during generation (default: same as --threads) |

| `--spec-draft-threads-batch, -tbd, --threads-batch-draft N` | number of threads to use during batch and prompt processing (default: same as --threads-draft) |

}

}

{

if (!cfg.empty()) {

try {

json json_settings = json::parse(cfg);

{ "endpoint_props", params.endpoint_props },

{ "endpoint_metrics", params.endpoint_metrics },

// New keys

// Deprecated: use ui/ui_settings instead (kept for backward compat)

{ "chat_template", tmpl_default },

{ "chat_template_caps", meta->chat_template_caps },

{ "bos_token", meta->bos_token_str },

{ "eos_token", meta->eos_token_str },

{ "build_info", meta->build_info },

{ "is_sleeping", queue_tasks.is_sleeping() },

};

if (params.use_jinja) {

if (!tmpl_tools.empty()) {

auto res = std::make_unique<server_http_res>();

res_ok(res, {

// TODO: add support for this on web UI

// this is a dummy response to make sure the UI doesn't break

{"model_alias", "llama-server"},

{"model_path", "none"},

{"n_ctx", 0},

}},

// New key

});

return res;

}

server_models models;

server_models_routes(const common_params & params, int argc, char ** argv)

: params(params), models(params, argc, argv) {

if (!cfg.empty()) {

try {

json json_settings = json::parse(cfg);