Struct DefaultParams 

pub struct DefaultParams {

    pub context_length: u32,
    pub threads: u32,
    pub threads_batch: u32,
    pub batch_size: u32,
    pub ubatch_size: u32,
    pub cache_type_k: Option<CacheTypeK>,
    pub cache_type_v: Option<CacheTypeV>,
    pub keep: i32,
    pub swa_full: bool,
    pub mlock: bool,
    pub mmap: bool,
    pub numa: NumMode,
    pub uniform_cache: bool,
    pub kv_cache_offload: bool,
    pub parallel: u32,
    pub max_concurrent_predictions: Option<u32>,
    pub system_prompt: String,
    pub system_prompt_preset_name: String,
    pub gpu_layers: i32,
    pub gpu_layers_mode: GpuLayersMode,
    pub split_mode: SplitMode,
    pub tensor_split: String,
    pub main_gpu: i32,
    pub fit: bool,
    pub lora: Option<PathBuf>,
    pub lora_scaled: Option<(PathBuf, f32)>,
    pub rpc: String,
    pub embedding: bool,
    pub flash_attn: bool,
    pub jinja: bool,
    pub chat_template: Option<String>,
    pub chat_template_kwargs: Option<String>,
    pub expert_count: i32,
    pub seed: i32,
    pub temperature: f32,
    pub top_k: i32,
    pub top_p: f32,
    pub min_p: f32,
    pub typical_p: f32,
    pub mirostat: Mirostat,
    pub mirostat_lr: f32,
    pub mirostat_ent: f32,
    pub ignore_eos: bool,
    pub samplers: Samplers,
    pub repeat_penalty: f32,
    pub repeat_last_n: i32,
    pub presence_penalty: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub dry_multiplier: f32,
    pub dry_base: f32,
    pub dry_allowed_length: i32,
    pub dry_penalty_last_n: i32,
    pub rope_scaling: RopeScaling,
    pub rope_scale: f32,
    pub rope_freq_base: f32,
    pub rope_freq_scale: f32,
    pub rope_yarn_enabled: bool,
    pub host: String,
    pub port: u16,
    pub timeout: u32,
    pub cache_prompt: bool,
    pub cache_reuse: u32,
    pub webui: bool,
    pub ws_server_enabled: bool,
    pub ws_server_port: u16,
    pub ws_server_auth_key: Option<String>,
    pub ws_server_tls_enabled: bool,
    pub ws_server_tls_cert: Option<String>,
    pub ws_server_tls_key: Option<String>,
    pub router_max_models: u32,
    pub server_mode: ServerMode,
    pub max_tokens: Option<u32>,
    pub cache_type: CacheType,
    pub backend: Backend,
    pub platform: Option<String>,
    pub llama_cpp_version_cpu: Option<String>,
    pub llama_cpp_version_vulkan: Option<String>,
    pub llama_cpp_version_rocm: Option<String>,
    pub llama_cpp_version_rocm_lemonade: Option<String>,
    pub llama_cpp_version_cuda: Option<String>,
    pub api_endpoint_enabled: bool,
    pub api_endpoint_port: u16,
    pub spec_type: String,
    pub draft_tokens: u32,
    pub tags: Vec<String>,
}

Fields

context_length: u32

threads: u32

threads_batch: u32

batch_size: u32

ubatch_size: u32

cache_type_k: Option<CacheTypeK>

cache_type_v: Option<CacheTypeV>

keep: i32

swa_full: bool

mlock: bool

mmap: bool

numa: NumMode

uniform_cache: bool

kv_cache_offload: bool

parallel: u32

max_concurrent_predictions: Option<u32>

system_prompt: String

system_prompt_preset_name: String

gpu_layers: i32

gpu_layers_mode: GpuLayersMode

split_mode: SplitMode

tensor_split: String

main_gpu: i32

fit: bool

lora: Option<PathBuf>

lora_scaled: Option<(PathBuf, f32)>

rpc: String

embedding: bool

flash_attn: bool

jinja: bool

chat_template: Option<String>

chat_template_kwargs: Option<String>

expert_count: i32

seed: i32

temperature: f32

top_k: i32

top_p: f32

min_p: f32

typical_p: f32

mirostat: Mirostat

mirostat_lr: f32

mirostat_ent: f32

ignore_eos: bool

samplers: Samplers

repeat_penalty: f32

repeat_last_n: i32

presence_penalty: Option<f32>

frequency_penalty: Option<f32>

dry_multiplier: f32

dry_base: f32

dry_allowed_length: i32

dry_penalty_last_n: i32

rope_scaling: RopeScaling

rope_scale: f32

rope_freq_base: f32

rope_freq_scale: f32

rope_yarn_enabled: bool

host: String

port: u16

timeout: u32

cache_prompt: bool

cache_reuse: u32

webui: bool

ws_server_enabled: bool

ws_server_port: u16

ws_server_auth_key: Option<String>

ws_server_tls_enabled: bool

ws_server_tls_cert: Option<String>

ws_server_tls_key: Option<String>

router_max_models: u32

server_mode: ServerMode

max_tokens: Option<u32>

cache_type: CacheType

backend: Backend

platform: Option<String>

Platform override: “linux”, “windows”, or “macos”. If None, auto-detected.

llama_cpp_version_cpu: Option<String>

llama_cpp_version_vulkan: Option<String>

llama_cpp_version_rocm: Option<String>

llama_cpp_version_rocm_lemonade: Option<String>

llama_cpp_version_cuda: Option<String>

api_endpoint_enabled: bool

api_endpoint_port: u16

spec_type: String

draft_tokens: u32

tags: Vec<String>

Trait Implementations

impl Clone for DefaultParams

fn clone(&self) -> DefaultParams

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for DefaultParams

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for DefaultParams

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for DefaultParams

where DefaultParams: Default,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<DefaultParams> for ModelSettings

fn from(dp: DefaultParams) -> Self

Converts to this type from the input type.

impl PartialEq for DefaultParams

fn eq(&self, other: &DefaultParams) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for DefaultParams

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for DefaultParams