Enum CacheRamHealth 

pub enum CacheRamHealth {
    LlamaDefault,
    DisabledByUser,
    DisabledInsufficientRam,
    Low {
        mb: u64,
    },
    Healthy {
        mb: u64,
    },
}

How healthy a resolved --cache-ram budget is, for user-facing display.

Exists so surfaces (dashboard, CLI) don’t re-derive the thresholds from magic numbers. In particular, a 0 budget is genuinely ambiguous at the call site — compute_auto_cache_ram_mb returns 0 when the machine can’t afford a cache, and a user can also pass --cache-ram-mb 0 — and those need different messages, since only one of them is a problem.

Variants

LlamaDefault

No --cache-ram flag emitted; llama-server’s built-in default applies.

DisabledByUser

The user asked for 0. Working as intended — not a warning.

DisabledInsufficientRam

Auto-sizing found no room after weights, KV, and headroom. The machine cannot afford a prompt cache at this model and context size.

Low

Working, but at or under CACHE_RAM_LOW_WATERMARK_BYTES — expect conversation switches to re-prefill more often than not.

Fields

mb: u64

Healthy

Comfortably sized.

Fields

mb: u64

Implementations

impl CacheRamHealth

pub const fn needs_attention(&self) -> bool

Whether this state is worth drawing the user’s attention to.

false for both healthy budgets and a deliberately disabled one — warning someone about a setting they chose is noise.

pub const fn budget_mb(&self) -> Option<u64>

The resolved budget in MiB, or None when no flag was emitted and llama-server’s own default applies.

Both disabled states report Some(0) rather than None: zero is a budget that was decided, and callers that treat “no flag” and “zero” alike would lose the distinction the enum exists to keep.

Trait Implementations

impl Clone for CacheRamHealth

fn clone(&self) -> CacheRamHealth

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CacheRamHealth

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

Formats the value using the given formatter.

impl PartialEq for CacheRamHealth

fn eq(&self, other: &CacheRamHealth) -> 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 Copy for CacheRamHealth

impl Eq for CacheRamHealth

impl StructuralPartialEq for CacheRamHealth