Struct PrimeWorkspaceShape 

pub struct PrimeWorkspaceShape {
    pub call_row_bytes: usize,
    pub prompt_row_bytes: usize,
    pub n_layers: usize,
}

The largest number of token rows any ONE mHC prime call carries under hyper_prime_ranges. Every per-call transient in the walk — the t*streams*hidden stream state, the MLA query planes, and the DSA indexer’s t * n_pools score plane — is proportional to this, so it is the single number a capacity assertion needs. Admission workspace shape of the NON-hyper prime (memra#144): the GDN / dense-MoE trunk (ornith, qwen-hybrid) and the step-TP trunk (step-3.7). prime_layers keeps its trunk transients in the retained prime slab pool sized by the CALL’s row count (prime_slabs_get): seven f32 [t, n_embd] planes (h, x1, z, xa, xb, ffn_out, mixed), two f16 mirrors (h16, z16), three f32 [t, n_ff_max] planes (act, gate, up), plus the per-call f16 activation (a16), the f16 pre-norm operand, and the x/hn copies the tail takes. The whole-prompt hiddens stack ([t, n_embd] f32) lives for the prime. Before this shape existed the admission line charged 0MB prefill-workspace on these paths, which is how a 164k ornith prompt was admitted onto a card that could not hold its monolithic prime (darklanes research/memra146-ornith-repro-20260904: 22 GB more resident after a 257k sweep with MEMRA_PRIME_CHUNK=0 than with 4096) and how a 91k step37 prompt stepped into a CUDA OOM after admission priced it at 3.1 GB.

Fields

call_row_bytes: usize

Bytes per row of ONE prime call (the slab planes above).

prompt_row_bytes: usize

Bytes per PROMPT row that live for the whole prime (the returned hiddens stack).

n_layers: usize

Trunk depth, for the auto chunk geometry (prime_chunk_tokens).

Implementations

impl PrimeWorkspaceShape

pub fn admission_bytes_with_call_rows( &self, prompt_rows: usize, call_rows: usize, ) -> usize

The charge for prompt_rows with an explicit per-call row count (pure arithmetic, what the tests pin).

pub fn admission_bytes(&self, prompt_rows: usize) -> usize

The charge under the deployment’s prime chunking: MEMRA_PRIME_CHUNK (0 = monolithic up to the launch cap, so the call rows are the whole prompt) or the auto geometry.

Trait Implementations

impl Clone for PrimeWorkspaceShape

fn clone(&self) -> PrimeWorkspaceShape

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for PrimeWorkspaceShape

impl Debug for PrimeWorkspaceShape

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

Formats the value using the given formatter.

impl Eq for PrimeWorkspaceShape

impl PartialEq for PrimeWorkspaceShape

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for PrimeWorkspaceShape