Struct ModelEntry 

pub struct ModelEntry {
    pub id: String,
    pub path: String,
    pub size_bytes: u64,
    pub arch: Option<String>,
    pub quant: Option<String>,
    pub context_length: Option<u64>,
    pub param_count: Option<u64>,
    pub state: ModelState,
    pub error: Option<String>,
    pub resident_bytes: Option<u64>,
}

One model the server can serve, described from its GGUF header alone. Nothing here requires reading a single weight.

Fields

id: String

Stable within a server run: the file stem for a .gguf, the directory name for a checkpoint directory. This is what LoadModelRequest takes, and the only way to name a model – there is deliberately no “load this path” endpoint.

path: String

Absolute path, for display. A client cannot ask the server to load an arbitrary one.

size_bytes: u64

On-disk size, summed across shards for a split checkpoint.

arch: Option<String>

general.architecture, verbatim. null when the header does not carry it.

quant: Option<String>

Quantization name (Q4_K_M, F16, …) from general.file_type when it maps to a name this server knows, else the dominant tensor dtype, else null. Never guessed from the filename.

context_length: Option<u64>

{arch}.context_length from the header.

param_count: Option<u64>

general.parameter_count when present, else the summed element count of every tensor in the header.

state: ModelState

error: Option<String>

Why the last load attempt failed. null unless state is ModelState::Error.

resident_bytes: Option<u64>

Bytes actually resident for this model. null for anything not loaded, and null for a loaded model whose footprint the server cannot measure – an mmap-resident checkpoint’s true RSS is a property of the page cache, not of this process, and reporting the file size as “resident” would be a lie in both directions.

Trait Implementations

impl Clone for ModelEntry

fn clone(&self) -> ModelEntry

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelEntry

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelEntry

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelEntry

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ModelEntry

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelEntry