Struct MemBudget 

pub struct MemBudget {
    pub free_vram: usize,
    pub free_pinnable_ram: usize,
}

Runtime free-memory budget (SPILLING-PLAN §2). Both numbers are QUERIED at load, never hardcoded — free host RAM “varies with other LLM servers”, so the split between pinned (Tier 1) and disk (Tier 2) must be decided against the live machine state.

Fields

free_vram: usize

Free VRAM in bytes, from cuMemGetInfo (authoritative; accounts for other GPU processes).

free_pinnable_ram: usize

Bytes of host RAM safe to pin: /proc/meminfo MemAvailable × pinned_frac (default 0.60). Capped so cudaHostAlloc can neither OOM nor evict the page cache the Tier-2 mmap depends on.

Implementations

impl MemBudget

pub fn probe(e: &Engine) -> Result<Self, Box<dyn Error>>

Trait Implementations

impl Clone for MemBudget

fn clone(&self) -> MemBudget

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for MemBudget

impl Debug for MemBudget

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

Formats the value using the given formatter.