Skip to main content

Module inference

Module inference 

Source
Expand description

inference category (reorg).

Re-exports§

pub use inference_agent as llm_agent;
pub use inference_awq as llm_awq;
pub use inference_bench as llm_bench;
pub use inference_eval as llm_eval;
pub use inference_gpu_profiler as llm_gpu_profiler;
pub use inference_kernel_parity as llm_kernel_parity;
pub use inference_modes::active_inference_mode;
pub use inference_modes::apply_mode_toggles;
pub use inference_modes::bootstrap_inference_mode;
pub use inference_modes::fast_verify_html_default;
pub use inference_modes::post_turn_verify_enabled;
pub use inference_modes::prefer_tensor_core_gemm;
pub use inference_modes::quant_graph_grounding_enabled;
pub use inference_modes::rights_mode_enabled;
pub use inference_modes::sentinel_mid_decode_enabled;
pub use inference_modes::set_inference_mode;
pub use inference_modes::InferenceMode;
pub use application_profile::active_application_profile;
pub use application_profile::apply_application_profile;
pub use application_profile::bootstrap_application_profile;
pub use application_profile::set_application_profile;
pub use application_profile::ApplicationProfile;
pub use post_turn_verify::maybe_verify_turn;
pub use post_turn_verify::return_html_as_text;
pub use post_turn_verify::verify_and_heal_turn;
pub use post_turn_verify::VerifiedTurn;
pub use post_turn_verify::VerifyCheck;
pub use inference_path_selector::apply_inference_path_plan;
pub use inference_path_selector::bootstrap_optimal_inference_path;
pub use inference_path_selector::format_path_plan;
pub use inference_path_selector::last_inference_path_plan;
pub use inference_path_selector::path_auto_enabled;
pub use inference_path_selector::resolve_inference_path_plan;
pub use inference_path_selector::run_path_select_cli;
pub use inference_path_selector::ComputeLane;
pub use inference_path_selector::InferencePathPlan;
pub use inference_path_selector::QuantProfile;
pub use quant_graph_grounding::export_fact_quins;
pub use quant_graph_grounding::fact_count;
pub use quant_graph_grounding::ground_generation;
pub use quant_graph_grounding::load_facts_from_tsv;
pub use quant_graph_grounding::lookup_capital_object;
pub use quant_graph_grounding::maybe_ground_generation;
pub use quant_graph_grounding::register_capital_fact;
pub use quant_graph_grounding::register_fact;
pub use quant_graph_grounding::reset_fact_store_to_defaults;
pub use quant_graph_grounding::seed_facts_from_bundled;
pub use quant_graph_grounding::GroundingFact;
pub use quant_graph_grounding::GroundingResult;
pub use quant_graph_grounding::CTX_GROUNDING;
pub use quant_graph_grounding::P_CAPITAL_OF;
pub use qualia_hybrid::apply_graph_logit_bias;
pub use qualia_hybrid::force_fact_tokens;
pub use qualia_hybrid::graph_force_enabled;
pub use qualia_hybrid::prepare_hybrid_decode;
pub use qualia_hybrid::propose_best_draft;
pub use qualia_hybrid::propose_fact_draft;
pub use qualia_hybrid::publish_graph_route_from_prompt;
pub use qualia_hybrid::publish_grounding_obligation;
pub use qualia_hybrid::publish_prompt_query_tensor;
pub use qualia_hybrid::GRAPH_LOGIT_BIAS;
pub use cuda_lane_stub as cuda_lane;
pub use speculative_decode::DominoMasker;
pub use speculative_decode::GrammarState;
pub use speculative_decode::GrammarStateMachine;
pub use speculative_decode::TokenTrie;
pub use speculative_decode::MAX_TRIE_DEPTH;
pub use semantic_skills::Scratchpad;
pub use semantic_skills::ScratchpadEntry;
pub use semantic_skills::ScratchpadError;
pub use semantic_skills::SearchResult;
pub use semantic_skills::StoredVector;
pub use semantic_skills::TextEmbedder;
pub use semantic_skills::Vector;
pub use semantic_skills::VectorStore;
pub use semantic_skills::DEFAULT_SCRATCHPAD_TTL;
pub use semantic_skills::EMBED_DIM;
pub use semantic_skills::MAX_SCRATCHPAD_ENTRIES;
pub use semantic_skills::MAX_VECTORS;
pub use etalon_tensor_bridge::build_forward_arena_on;
pub use etalon_tensor_bridge::build_fused_attention_on;
pub use etalon_tensor_bridge::build_topk_pipeline_on;
pub use etalon_tensor_bridge::try_shared_forward_arena;
pub use etalon_tensor_bridge::try_shared_fused_attention;
pub use etalon_tensor_bridge::try_shared_topk_pipeline;

Modules§

agent
Agent-identifier model (#16): resolve an identifier’s AGENT TYPE and check grounding.
ambient_orchestration
Ambient Sub-Threshold Orchestration Implementation
application_profile
Application profiles — how inference is used, not only which GPU path.
compute_universe
Qualia-native compute universe fabric (Track B2).
conditioning
Portable conditioning compiler (Prompt Precision P1C).
conditioning_eval
Cold, bounded evaluation API for prompt precision (Prompt Precision P5).
conditioning_opt
Model mapping and precision optimization pipeline.
cuda_lane_stub
Stub when CUDA feature is off — CUDA lane APIs return false / no-op.
domino_gbnf
DOMINO GBNF Constrained LLM Decoding for VibeScript.
etalon_tensor_bridge
Bridge between etalon-tensor accelerated operators and QualiaDB inference.
ggml_quants
Canonical numerical encodings and descriptor helpers, with legacy Qualia paths.
gguf_sharder
Q-GGUF Hybrid Packaging Parses monolithic .gguf files: vocabulary (KV section) and tensor names/offsets (tensor-info section) are extracted into native Rust types; multi-gigabyte tensor payloads are left on disk for direct VRAM mapping via gguf_bridge.rs.
inference_agent
inference_awq
W1/AWQ — activation-statistics capture for Activation-aware Weight Quantization (no external libs).
inference_bench
A0 — native LLM benchmark harness (STELLAR §A; decisions D17 + D22).
inference_eval
W1 — in-project quality oracle (no external libs): perplexity, KL-divergence, and a coherence ratio, measured by teacher-forcing an eval corpus through the engine and comparing a candidate model’s output distribution against a higher-fidelity reference’s.
inference_gpu_profiler
Per-kernel GPU timing for the native LLM forward/decode path (W2 / D17).
inference_kernel_parity
W3 — in-project GPU↔CPU kernel-parity oracle (no external LLM libs).
inference_modes
Multi-mode inference — keep parallel approaches, do not dump one pipeline.
inference_path_selector
Device-optimal inference path selection.
kv_capture
W5b — KV-vector capture hook for sparse-dictionary calibration.
kv_dict
W5b Phase 4b — the KV-dictionary type and its sparse codec, in CORE.
kv_dict_runtime
W5b Phase 4b — runtime KV-dictionary install + reconstruction, in CORE (engine-side, no forge dep).
lab
Inference superiority lab — instruments for evidence-based methodology.
metal_lane
Shared-device and host-policy adapter for the canonical Metal lane.
moe
Mixture-of-Experts (MoE) execution and offload engine (Work Packages F9, F10).
neuro_symbolic_sieve
Grammar-constrained FSM sieve for neuro-symbolic LLM output (zero-heap hot path).
operator_converter
Compatibility forwarding to the canonical Etalon owner.
operator_package
Compatibility forwarding to the canonical Etalon owner.
operator_runtime
Compatibility forwarding to the canonical Etalon owner.
orchestrator
The Orchestration Sieve — LLM Sub-Agent Dispatch Layer
paged_kv
Compatibility exports for the production paged-KV runtime.
post_turn_verify
Post-turn verification — “generate first, heal second”.
prompt_lookup
W6a — prompt-lookup (n-gram) speculative decoding: the proposer.
qualia_hybrid
Qualia-unique hybrid inference: graph + manifold + modes + deontic.
quant_graph_grounding
QuantGraph mode — selective grounding / repair against a NQuin fact graph.
qwen
Qwen hybrid architecture execution and state management (Work Package F11).
reranker
Cross-encoder reranker for candidate re-scoring.
residency_planner
STELLAR §A AH-track H2 — residency + device-priority planner (decisions D24/D25/D30/D31).
resident_model
Process-wide resident GGUF mmap — released explicitly on model eviction.
runtime
Prepared native inference runtime.
safetensor
Phase 6 / task #12 — safetensor (+ MLX) source parsing + dtype gate for the streaming transcoder (p64_weight::transcode_safetensor_to_p64).
safetensor_loader
Safetensor model loader — native zero-copy adoption of Safetensors models (including BF16).
sampler
W2 — exact CPU sampling chain for decode.
semantic_culler
Semantic Culler - Pre-GPU pipeline for agency-driven data filtering
semantic_skills
A9 — Semantic Skills: Vectors, Embeddings & Scratchpads.
sparse_cache
spatial_sieve
speculative_decode
A2 — Speculative Constrained Decoding (DOMINO).
tensor_roles
Canonical tensor identities and the preserved FFN precision selection policy.
ternary
BitNet b1.58 ternary quantization codec — STELLAR §A compression (task #12).
ternary_gpu
Task #12 / STELLAR §A — native GPU dispatch of the ternary GEMM + on-device parity.
thermal_telemetry
W7 — real GPU thermal/power telemetry + a detect-and-recommend thermal governor.
thermal_wal
topk
topk_gpu
STELLAR §A A1a — native GPU dispatch of the top-K reduction + on-device parity.

Structs§

AttentionParams
Legacy attention configuration. Use FusedAttentionParams for GPU uniform bindings.
CudaMegaPassExecutor
Scalar transformer reference executor with a resident KV cache.
DirectMlComputeLane
DirectML / DX12 compute executor lane supporting both tiled host execution and Etalon GPU compute pipeline dispatch.
DmlGemmOp
DirectML 2D matrix multiplication operator ($C = A_{m \times k} \times B_{k \times n}$).
DmlGemmParams
ForwardArena
Unified forward execution arena on an Etalon device.
FusedAttentionPipeline
GPU compute pipeline for fused FlashAttention dispatch.
LogitMaskHeader
80-byte std140-aligned logit mask header containing the 512-bit sieve bitmask and autoregressive sampling hyper-parameters.
PagedKvBlockTable
TensorView
TopkParams
Uniform parameters matching the WGSL Params layout in topk_reduction.wgsl.
TopkReductionPipeline
Complete GPU compute pipeline for block top-k / argmax reduction.

Enums§

ForwardMode
Operational mode of the forward execution arena.
KvCacheLayout
QuantScheme

Constants§

FUSED_ATTENTION_WGSL
Raw WGSL shader source for the fused FlashAttention kernel with guarded all-masked row handling.
TOPK_REDUCTION_WGSL
Raw WGSL shader source for the GPU block top-k reduction kernel.

Functions§

online_softmax_rescale
Numerical online-softmax rescale calculation with guarded all-masked row handling.

Type Aliases§

CapturedCudaMegaPass
DmlLane