Module inference 

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::cache_dense_weight;

pub use cuda_lane::clear_weight_cache;

pub use cuda_lane::dense_weight_cached;

pub use cuda_lane::device_kv_ready;

pub use cuda_lane::ensure_device_kv_cache;

pub use cuda_lane::preload_resident_blob;

pub use cuda_lane::prepare_mega_pass_kernels;

pub use cuda_lane::q4k_device_weight_count;

pub use cuda_lane::q4k_weight_resident;

pub use cuda_lane::q8_0_gemv_oracle_into;

pub use cuda_lane::try_cuda_batch_gemv;

pub use cuda_lane::try_cuda_batch_gemv_cached;

pub use cuda_lane::try_cuda_batch_gemv_cached_only;

pub use cuda_lane::try_cuda_mega_pass;

pub use cuda_lane::try_q4k_soa_attention_device;

pub use cuda_lane::try_q4k_soa_ffn_block;

pub use cuda_lane::try_q4k_soa_ffn_block_residual;

pub use cuda_lane::try_q4k_soa_fused_swiglu;

pub use cuda_lane::try_q4k_soa_gemv;

pub use cuda_lane::try_q4k_soa_qkv;

pub use cuda_lane::try_q8_0_cuda_gemv;

pub use cuda_lane::warm_cuda_context;

pub use cuda_lane::weight_cache_len;

pub use cuda_lane::weight_fingerprint;

pub use cuda_lane::MegaPassLayerDims;

pub use cuda_lane::MegaPassLayerWeights;

pub use cuda_lane::MegaPassPlanView;

pub use cuda_lane::MegaPassWeightLayout;

pub use cuda_lane::MAX_DENSE_ELEMS;

pub use cuda_lane::Q8_0_BLOCK_BYTES;

pub use cuda_lane::Q8_0_BLOCK_ELEMS;

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).

cuda_lane

CUDA inference lane — dense batch GEMM via persistent WMMA (mode=cuda).

ggml_quants

GGML quantization block layout and zero-heap row dequantization.

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

Metal mega-pass orchestrator: chain all transformer layers into one Metal command buffer with a single fence at the end. No per-layer readback.

neuro_symbolic_sieve

Grammar-constrained FSM sieve for neuro-symbolic LLM output (zero-heap hot path).

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.

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).

sampler

W2 — exact CPU sampling chain for decode.

semantic_culler

Semantic Culler - Pre-GPU pipeline for agency-driven data filtering

sparse_cache

spatial_sieve

tensor_roles

Task #12 / STELLAR §A — tensor-name → engine GEMM-role mapping + the ternary 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

STELLAR §A A1a — GPU top-K reduction: CPU oracle, host merge, and the WGSL kernel.

topk_gpu

STELLAR §A A1a — native GPU dispatch of the top-K reduction + on-device parity.