Struct Limits 

pub struct Limits {

    pub memory_gb: f64,
    pub context_tokens: usize,
    pub prefix_cache_mib: usize,
    pub cache_max_entries: usize,
    pub cache_idle_seconds: u64,
    pub queued_requests: usize,
    pub http_readers: usize,
    pub request_bytes: usize,
    pub max_output_tokens: usize,
    pub active_requests: usize,
    pub active_state_mib: usize,
    pub prefill_quantum: usize,
    pub prefill_chunk_seconds: f64,
    pub max_sessions: usize,
    pub session_history_mib: usize,
    pub session_idle_seconds: u64,
    pub response_bytes: usize,
}

Fields

memory_gb: f64

Metal allocations plus reserved prefix cache, not whole-process RSS.

context_tokens: usize

prefix_cache_mib: usize

cache_max_entries: usize

cache_idle_seconds: u64

Zero disables time-based expiry; the byte and entry limits still apply.

queued_requests: usize

http_readers: usize

request_bytes: usize

max_output_tokens: usize

active_requests: usize

active_state_mib: usize

prefill_quantum: usize

prefill_chunk_seconds: f64

Target chunk duration when requests compete; 0 disables pacing.

max_sessions: usize

session_history_mib: usize

session_idle_seconds: u64

response_bytes: usize

Trait Implementations

impl Clone for Limits

fn clone(&self) -> Limits

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Limits

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

Formats the value using the given formatter.

impl Default for Limits

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Limits

where Limits: Default,

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Limits

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for Limits

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 Limits