Struct llama_model_quantize_params

Source

#[repr(C)]
pub struct llama_model_quantize_params {Show 29 fields
    pub nthread: i32,
    pub ftype: llama_ftype,
    pub output_tensor_type: ggml_type,
    pub token_embedding_type: ggml_type,
    pub per_layer_token_embedding_type: ggml_type,
    pub attn_q_type: ggml_type,
    pub attn_k_type: ggml_type,
    pub attn_v_type: ggml_type,
    pub attn_qkv_type: ggml_type,
    pub attn_output_type: ggml_type,
    pub ffn_gate_type: ggml_type,
    pub ffn_down_type: ggml_type,
    pub ffn_up_type: ggml_type,
    pub ffn_gate_inp_type: ggml_type,
    pub extra_output_type: ggml_type,
    pub allow_requantize: bool,
    pub quantize_output_tensor: bool,
    pub only_copy: bool,
    pub pure_: bool,
    pub keep_split: bool,
    pub ignore_imatrix_rules: bool,
    pub only_repack: bool,
    pub dry_run: bool,
    pub partial_requant: bool,
    pub imatrix: *mut c_void,
    pub kv_overrides: *mut c_void,
    pub custom_quants: *mut c_void,
    pub repack_pattern: *mut c_void,
    pub user_data: *mut quantize_user_data,
}

Fields§

§nthread: i32§ftype: llama_ftype§output_tensor_type: ggml_type§token_embedding_type: ggml_type§per_layer_token_embedding_type: ggml_type§attn_q_type: ggml_type§attn_k_type: ggml_type§attn_v_type: ggml_type§attn_qkv_type: ggml_type§attn_output_type: ggml_type§ffn_gate_type: ggml_type§ffn_down_type: ggml_type§ffn_up_type: ggml_type§ffn_gate_inp_type: ggml_type§extra_output_type: ggml_type§allow_requantize: bool§quantize_output_tensor: bool§only_copy: bool§pure_: bool§keep_split: bool§ignore_imatrix_rules: bool§only_repack: bool§dry_run: bool§partial_requant: bool§imatrix: *mut c_void§kv_overrides: *mut c_void§custom_quants: *mut c_void§repack_pattern: *mut c_void§user_data: *mut quantize_user_data

llama_model_quantize_params

Struct llama_model_quantize_params Copy item path

Fields§

Trait Implementations§

impl Clone for llama_model_quantize_params

fn clone(&self) -> llama_model_quantize_params

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

impl Copy for llama_model_quantize_params

impl Debug for llama_model_quantize_params

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

impl PartialEq for llama_model_quantize_params

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

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

impl StructuralPartialEq for llama_model_quantize_params

Auto Trait Implementations§

impl !Send for llama_model_quantize_params

impl !Sync for llama_model_quantize_params

impl Freeze for llama_model_quantize_params

impl RefUnwindSafe for llama_model_quantize_params

impl Unpin for llama_model_quantize_params

impl UnsafeUnpin for llama_model_quantize_params

impl UnwindSafe for llama_model_quantize_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_model_quantize_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>,