Struct Fp8BlockScaledFormat 

pub struct Fp8BlockScaledFormat {
    pub ignore_modules: Vec<String>,
}

FP8 block-scaled checkpoint.

Fields

ignore_modules: Vec<String>

Implementations

impl Fp8BlockScaledFormat

pub fn new(ignore_modules: Vec<String>) -> Self

Trait Implementations

impl Debug for Fp8BlockScaledFormat

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

Formats the value using the given formatter.

impl QuantFormat for Fp8BlockScaledFormat

fn name(&self) -> &'static str

Human-readable name for logs ("modelopt", "compressed-tensors", "fp8-blockscaled").

fn base_variant(&self) -> Nvfp4Variant

The Nvfp4Variant that this format maps to in the existing weight_map.rs dispatch. Allows the trait to co-exist with the legacy variant-based call sites during incremental migration.

fn is_ignored(&self, module_path: &str) -> bool

Is module_path in the format’s ignore list (should be loaded as dense BF16 rather than quantized)? module_path is the tensor name with the trailing .weight_scale_2 / .weight_packed / etc. stripped — i.e. the prefix passed to weight_map::quantized_any.

fn variant_for(&self, module_path: &str) -> Nvfp4Variant

Effective variant for a specific module: the base variant, or Bf16Raw if the module is in the ignore list. Loaders should consult this instead of base_variant when loading per-module.