Module compute_universe 

Qualia-native compute universe fabric (Track B2).

This is not a generic GPU scheduler. Universes U0/U1/U2 map to QualiaDB primitives:

1. Graph–tensor duality — NQuin graph and Tensor10D SOA share one resident substrate (U1 pin).
2. Phase-8 bifurcation — lock-free SPSC rings between U0 (LLM), Sentinel, and U1 (tensor).
3. Sentinel governance — DenyRollback on the control ring before the next token matmul.
4. VramLedger pins — Full / Eco / Reserve per universe; U0 KV protected in Reserve.

One physical wgpu::Device (gpu_context::shared_gpu); logical parallelism via queues + rings.

Structs

AttentionRouteMask

U1 output: sparse attention routing bitmask for U0 matmul (10D kNN filter).

ContextInjectRing

Fixed-capacity SPSC context ring (producer U1, consumer U0).

ContextInjectToken

Lightweight pointer pushed U1→U0 (48 B NQuin stays in SOA; ring carries index + hash).

GraphTensorSubstrate

Resident graph↔tensor SOA visible to U1 (write/search), U0 (read/inject), U2 (render).

TopologyDraftBatch

Draft batch pushed U1→U0 for parallel verify (no draft-model weights).

TopologyDraftRing

UniverseFabric

Qualia fabric: ledger orchestration + shared substrate + Phase-8 context ring.

Enums

Phase8Channel

Phase-8 bifurcation ring (see llm_agent.rs LogitStream / ControlStream + U1 inject).

QualiaPrimitive

Qualia engine primitive exploited by a compute universe (not portable DB semantics).

Constants

ATTENTION_MASK_WORDS

CONTEXT_INJECT_RING_CAP

KV_ATTENTION_MASK_WORDS

KV cache bitmask for fused_attention.wgsl (1024 context slots).

MAX_DRAFT_LEN

TOPOLOGY_DRAFT_RING_CAP

Functions

attention_kv_mask_u32

Map U1 route mask (tensor indices) → KV slot mask for attention (B3.2b light).

attention_mask_seq

attention_route_mask

build_attention_route_mask

B3.2a — kNN hits → sparse attention bitmask (zero-heap).

context_inject_ring

extrapolate_topology_draft

Extrapolate γ concept hashes from kNN trajectory (B3.1b); optional TopologyDraftMapper (B3.1c).

extrapolate_topology_draft_mapped

load_query_tensor

pop_tensor_context

U0 decode loop pulls injected graph context (non-blocking).

pop_topology_draft

publish_attention_route_mask

Publish U1 route mask snapshot (producer / tests).

publish_decode_hint

U0 publishes the active decode position for the U1 producer (non-blocking).

publish_query_tensor

U0 publishes the 10D query anchor U1 should search around.

push_tensor_context

Record a tensor kNN hit for async U0 consumption (continuous RAG path).

push_tensor_search_hits

B2.4 producer hook: push kNN indices from visit_tensor_search / tensor_search_into.

query_subject_hash

run_tensor_search_producer_cycle

One U1 producer cycle: search resident SOA, push ring, refresh mask, draft topology.

sentinel_allows_topology_draft

Phase-8 Sentinel gate for U1→U0 topology drafts (B3.1d polish).

start_tensor_search_producer

B3.3a — spawn background U1 tensor search producer (idempotent).

stop_tensor_search_producer

topology_draft_ring