StateBudget

Struct StateBudget 

Source
pub struct StateBudget {
    pub kda_recurrent: usize,
    pub kda_conv: usize,
    pub dsa_kv_per_token: usize,
    pub dsa_indexer_per_token: usize,
    pub mhc_highway_per_token: usize,
    pub moe_routing_per_token: usize,
}
Expand description

2026-09-25: Per-sequence state bytes, built by Glm5NextTextSkeleton::state_budget from the config’s geometry. per_rank divides only the KDA state and the DSA KV.

Fields§

§kda_recurrent: usize

2026-09-25: KDA recurrent state, [heads, head_dim, head_dim] fp32 per KDA layer, summed over the KDA layers. Does not grow with sequence length.

§kda_conv: usize

2026-09-25: KDA causal-conv window, bf16, conv_dim x (kernel - 1 + num_spec) per KDA layer. Does not grow with sequence length.

§dsa_kv_per_token: usize

2026-09-25: DSA MLA KV per token across the text-stack DSA layers, kv_lora_rank x 2 bytes each. Grows with sequence length.

§dsa_indexer_per_token: usize

2026-09-25: Indexer key and gate state per token across the text-stack DSA layers. Grows with sequence length. The indexer projections are DsaShard::Replicated (glm5next_dsa/tp.rs), so every rank holds the whole cache and Self::per_rank does not divide it.

§mhc_highway_per_token: usize

2026-09-25: mHC highway per token, hc_mult x hidden fp32. An activation, so neither fixed nor per_token counts it.

§moe_routing_per_token: usize

2026-09-25: MoE routing scratch per token: f32 logits plus 4-byte top-k ids and weights.

Implementations§

Source§

impl StateBudget

Source

pub fn fixed(&self) -> usize

2026-09-25: Fixed (sequence-length-independent) bytes per sequence.

Source

pub fn per_token(&self) -> usize

2026-09-25: Bytes that grow with every token of context.

Source

pub fn for_sequence(&self, tokens: usize) -> usize

2026-09-25: Total persistent state for a sequence of tokens.

Source

pub fn per_rank(&self, ep: usize) -> StateBudget

2026-09-25: Divides kda_recurrent, kda_conv and dsa_kv_per_token by ep; the indexer cache, the mHC highway and the routing scratch stay whole.

Trait Implementations§

Source§

impl Clone for StateBudget

Source§

fn clone(&self) -> StateBudget

Returns a duplicate of the value. Read more
1.0.0 · Source§

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

Performs copy-assignment from source. Read more
Source§

impl Debug for StateBudget

Source§

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

Formats the value using the given formatter. Read more
Source§

impl Copy for StateBudget

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> CloneToUninit for T
where T: Clone,

Source§

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dest. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

§

impl<T> Instrument for T

§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided [Span], returning an Instrumented wrapper. Read more
§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<T> ToOwned for T
where T: Clone,

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

§

fn vzip(self) -> V

§

impl<T> WithSubscriber for T

§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

§

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

§

impl<T> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,