Struct PrefixedLoader 

pub struct PrefixedLoader<'a, B: Backend> { /* private fields */ }

Adapter that prepends a fixed prefix to every tensor name before delegating to an underlying loader.

Use case: a single safetensors file contains a sub-model (e.g. Qwen3-TTS stores the Talker LM under talker.model.*) and we want to reuse a backbone loader like LlamaFamilyModel::new that expects bare model.* names. Wrapping with PrefixedLoader { inner, prefix: "talker." } lets the backbone code stay prefix-agnostic.

Implementations

impl<'a, B: Backend> PrefixedLoader<'a, B>

pub fn new(inner: &'a dyn WeightLoader<B>, prefix: impl Into<String>) -> Self

Trait Implementations

impl<'a, B: Backend> WeightLoader<B> for PrefixedLoader<'a, B>

fn load_tensor(&self, name: &str) -> Result<B::Buffer>

Load a single tensor by fully qualified name (e.g. "model.embed_tokens.weight").

fn load_linear(&self, name: &str) -> Result<Box<dyn Linear<B>>>

Load a projection as a Linear<B>. The concrete implementation (DenseLinear / GptqLinear / AwqLinear / GgufLinear) depends on the loader’s file format and quant config.

fn has_tensor(&self, name: &str) -> bool

Whether a tensor with this name exists in the source.

fn quant_config(&self) -> Option<&QuantConfig>

Quantization metadata (parsed from quantize_config.json or a GGUF header). None means the source is dense.