Struct QuantizationConfig 

pub struct QuantizationConfig {
    pub quant_method: String,
    pub format: String,
    pub config_groups: HashMap<String, ConfigGroup>,
    pub ignore: Vec<String>,
    pub teenygrad_packed_int4: HashMap<String, PackedTensorInfo>,
}

The full quantization_config metadata blob embedded in the output .safetensors header.

Fields

quant_method: String

Always "compressed-tensors".

format: String

"int-quantized", "float-quantized", or "pack-quantized".

config_groups: HashMap<String, ConfigGroup>

Named config groups (today, always a single "group_0").

ignore: Vec<String>

Tensor names left unquantized (see should_quantize).

teenygrad_packed_int4: HashMap<String, PackedTensorInfo>

teeny-quant extension: logical shape for each nibble-packed INT4 tensor.

Trait Implementations

impl Clone for QuantizationConfig

fn clone(&self) -> QuantizationConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizationConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuantizationConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for QuantizationConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.