Struct llama_context_params

Source

#[repr(C)]
pub struct llama_context_params {Show 65 fields
    pub seed: u32,
    pub n_ctx: u32,
    pub n_batch: u32,
    pub n_ubatch: u32,
    pub n_seq_max: u32,
    pub n_threads: u32,
    pub n_threads_batch: u32,
    pub max_extra_alloc: i32,
    pub worst_case_tokens: i32,
    pub rope_scaling_type: llama_rope_scaling_type,
    pub pooling_type: llama_pooling_type,
    pub attention_type: llama_attention_type,
    pub rope_freq_base: f32,
    pub rope_freq_scale: f32,
    pub yarn_ext_factor: f32,
    pub yarn_attn_factor: f32,
    pub yarn_beta_fast: f32,
    pub yarn_beta_slow: f32,
    pub yarn_orig_ctx: u32,
    pub defrag_thold: f32,
    pub cb_eval: ggml_backend_sched_eval_callback,
    pub cb_eval_user_data: *mut c_void,
    pub type_k: ggml_type,
    pub type_v: ggml_type,
    pub idx_type_k: ggml_type,
    pub type_reduce: ggml_type,
    pub type_graph_attn: ggml_type,
    pub type_k_first: ggml_type,
    pub type_k_last: ggml_type,
    pub type_v_first: ggml_type,
    pub type_v_last: ggml_type,
    pub n_k_first: i32,
    pub n_k_last: i32,
    pub n_v_first: i32,
    pub n_v_last: i32,
    pub logits_all: bool,
    pub embeddings: bool,
    pub offload_kqv: bool,
    pub flash_attn: bool,
    pub mla_attn: c_int,
    pub attn_max_batch: c_int,
    pub fused_moe_up_gate: bool,
    pub grouped_expert_routing: bool,
    pub fused_up_gate: bool,
    pub fused_mmad: bool,
    pub rope_cache: bool,
    pub graph_reuse: bool,
    pub dsa: bool,
    pub fused_idx_topk: bool,
    pub dsa_top_k: c_int,
    pub min_experts: c_int,
    pub thresh_experts: f32,
    pub only_active_experts: bool,
    pub prefetch_experts: bool,
    pub prefetch_experts_threads: c_int,
    pub k_cache_hadamard: bool,
    pub v_cache_hadamard: bool,
    pub split_mode_graph_scheduling: bool,
    pub scheduler_async: bool,
    pub mtp: bool,
    pub mtp_op_type: llama_mtp_op_type,
    pub abort_callback: ggml_abort_callback,
    pub abort_callback_data: *mut c_void,
    pub offload_policy: *mut c_void,
    pub cuda_params: *mut c_void,
}

Fields§

§seed: u32§n_ctx: u32§n_batch: u32§n_ubatch: u32§n_seq_max: u32§n_threads: u32§n_threads_batch: u32§max_extra_alloc: i32§worst_case_tokens: i32§rope_scaling_type: llama_rope_scaling_type§pooling_type: llama_pooling_type§attention_type: llama_attention_type§rope_freq_base: f32§rope_freq_scale: f32§yarn_ext_factor: f32§yarn_attn_factor: f32§yarn_beta_fast: f32§yarn_beta_slow: f32§yarn_orig_ctx: u32§defrag_thold: f32§cb_eval: ggml_backend_sched_eval_callback§cb_eval_user_data: *mut c_void§type_k: ggml_type§type_v: ggml_type§idx_type_k: ggml_type§type_reduce: ggml_type§type_graph_attn: ggml_type§type_k_first: ggml_type§type_k_last: ggml_type§type_v_first: ggml_type§type_v_last: ggml_type§n_k_first: i32§n_k_last: i32§n_v_first: i32§n_v_last: i32§logits_all: bool§embeddings: bool§offload_kqv: bool§flash_attn: bool§mla_attn: c_int§attn_max_batch: c_int§fused_moe_up_gate: bool§grouped_expert_routing: bool§fused_up_gate: bool§fused_mmad: bool§rope_cache: bool§graph_reuse: bool§dsa: bool§fused_idx_topk: bool§dsa_top_k: c_int§min_experts: c_int§thresh_experts: f32§only_active_experts: bool§prefetch_experts: bool§prefetch_experts_threads: c_int§k_cache_hadamard: bool§v_cache_hadamard: bool§split_mode_graph_scheduling: bool§scheduler_async: bool§mtp: bool§mtp_op_type: llama_mtp_op_type§abort_callback: ggml_abort_callback§abort_callback_data: *mut c_void§offload_policy: *mut c_void§cuda_params: *mut c_void

llama_context_params

Struct llama_context_params Copy item path

Fields§

Trait Implementations§

impl Clone for llama_context_params

fn clone(&self) -> llama_context_params

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

impl Copy for llama_context_params

impl Debug for llama_context_params

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

impl PartialEq for llama_context_params

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

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

impl StructuralPartialEq for llama_context_params

Auto Trait Implementations§

impl !Send for llama_context_params

impl !Sync for llama_context_params

impl Freeze for llama_context_params

impl RefUnwindSafe for llama_context_params

impl Unpin for llama_context_params

impl UnsafeUnpin for llama_context_params

impl UnwindSafe for llama_context_params

Blanket Implementations§

impl<T> Any for Twhere T: 'static + ?Sized,

fn type_id(&self) -> TypeId

impl<T> Borrow<T> for Twhere T: ?Sized,

fn borrow(&self) -> &T

impl<T> BorrowMut<T> for Twhere T: ?Sized,

fn borrow_mut(&mut self) -> &mut T

impl<T> CloneToUninit for Twhere T: Clone,

unsafe fn clone_to_uninit(&self, dest: *mut u8)

impl<T> From<T> for T

fn from(t: T) -> T

impl<T, U> Into<U> for Twhere U: From<T>,

fn into(self) -> U

impl<T> ToOwned for Twhere T: Clone,

type Owned = T

fn to_owned(&self) -> T

fn clone_into(&self, target: &mut T)

impl<T, U> TryFrom<U> for Twhere U: Into<T>,

type Error = Infallible

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

impl<T, U> TryInto<U> for Twhere U: TryFrom<T>,

type Error = <U as TryFrom<T>>::Error

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Struct llama_context_params

impl<T> Any for T
where T: 'static + ?Sized,

impl<T> Borrow<T> for T
where T: ?Sized,

impl<T> BorrowMut<T> for T
where T: ?Sized,

impl<T> CloneToUninit for T
where T: Clone,

impl<T, U> Into<U> for T
where U: From<T>,

impl<T> ToOwned for T
where T: Clone,

impl<T, U> TryFrom<U> for T
where U: Into<T>,

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,