Introduction
Getting Started
1.
Installation
2.
Quick Start
3.
Project Structure
Core Concepts
4.
The APR Format
5.
Model Bundling
6.
Format Conversion
7.
Zero-Copy Loading
Category A: Model Creation
8.
Overview
9.
Create APR from Scratch
10.
Linear Regression Model
11.
Decision Tree Model
12.
K-Means Clustering
13.
N-gram Language Model
14.
Neural Network
Category B: Binary Bundling
15.
Overview
16.
Bundle Static Model
17.
Bundle Quantized Model
18.
Bundle Encrypted Model
19.
Static Binary Embedding
20.
Q4 Quantization
21.
Signed Models
22.
Lambda Package
Category C: Training
23.
Overview
24.
Incremental Training
25.
Online Learning
26.
Federated Simulation
27.
Curriculum Learning
28.
Autograd Training
29.
LoRA Fine-tuning
30.
QLoRA Fine-tuning
31.
Knowledge Distillation
32.
Model Merge
33.
Evaluation Metrics
34.
Hyperparameter Sweep
35.
Checkpoint Resume
36.
Mixed-Precision Training
37.
Few-Shot Fine-tuning
38.
Gradient Accumulation
39.
Learning Rate Schedules
40.
Data Preprocessing
41.
Custom Autograd Ops
42.
Gradient Clipping
43.
Backprop Visualization
Category D: Format Conversion
44.
Overview
45.
SafeTensors to APR
46.
APR to GGUF
47.
GGUF to APR
48.
Phi Model to APR
49.
ONNX to APR
Category E: Model Registry
50.
Overview
51.
Register APR Model
52.
Model Lineage
53.
Model Comparison
54.
Model Rollback
55.
Model Versioning
Category F: API Integration
56.
Overview
57.
Model Inference
58.
Streaming Inference
59.
Batch Inference
60.
Health Check
61.
Auth Middleware
Category G: Serverless
62.
Overview
63.
Lambda Inference
64.
Cold Start Optimization
65.
Edge Functions
66.
Container Image
67.
Model Warmup
Category H: WASM/Browser
68.
Overview
69.
Browser Inference
70.
Web Workers
71.
Progressive Loading
72.
WebGPU Acceleration
73.
Streaming Compilation
74.
Model Loader
Category I: GPU Acceleration
75.
Overview
76.
FlashAttention
77.
CUDA Inference
78.
Tensor Core Optimization
79.
Multi-GPU Inference
80.
Memory Management
81.
Memory Pool
82.
PTX Analysis
83.
Vulkan Inference (Intel Arc)
Category J: SIMD Acceleration
84.
Overview
85.
Matrix Operations
86.
Vectorized Inference
87.
Quantized Operations
88.
Auto-Vectorization
89.
AVX-VNNI Int8 Inference
Category K: Model Distillation
90.
Overview
91.
Knowledge Transfer
92.
Layer Matching
93.
Pruning-Aware Distillation
94.
Quantization-Aware Distillation
95.
Structured Pruning
96.
Attention Transfer
97.
Self-Distillation
Category L: CLI Tools
98.
Overview
99.
apr-info
100.
apr-bench
101.
apr-convert
102.
apr-serve
103.
apr-diff
104.
apr-tui
105.
apr-decrypt
106.
apr-diagnose
107.
apr-list
108.
apr-rm
109.
apr-runs
110.
apr-tokenize
111.
apr-ptx-map
Category M: Inference Monitoring
112.
Overview
113.
Inference Explainability
114.
Hash Chain Audit
115.
Cost Tracking
116.
Latency Histogram
117.
Drift Detection
118.
Headless cbtop
119.
Energy Estimation
120.
Memory Profiler
Category N: Speech Recognition
121.
Overview
122.
Whisper Transcription
123.
Streaming ASR
124.
Voice Activity Detection
125.
Speaker Diarization
126.
Multilingual Identification
Category O: Distributed Computing
127.
Overview
128.
Distributed Inference
129.
Model Sharding
130.
Ring AllReduce
131.
Pipeline Parallelism
132.
Gossip Protocol
Category P: Inference Patterns
133.
Overview
134.
Simple Inference
135.
Speculative Decoding
136.
KV-Cache Chat
137.
Multi-turn Chat
138.
Tool Use
139.
Streaming Tokens
140.
Adaptive Batching
141.
Dynamic Batch SLA
142.
Ensemble Inference
143.
Model Pipeline
144.
Quantized Comparison
145.
APR Run
146.
Mmap Lazy Loading
Category Q: Model Serving
147.
Overview
148.
HTTP Model Server
149.
A/B Testing
150.
Canary Deploy
151.
Rate Limiter
152.
Selection Router
Category R: Model Optimization
153.
Overview
154.
Full Pipeline
155.
LoRA Fine-tuning
156.
QLoRA Fine-tuning
157.
Adapter Merge
158.
VRAM Planning
159.
Magnitude Pruning
160.
Structured Pruning
161.
Depth Pruning
162.
Wanda Pruning
163.
Gradual Schedule
164.
Standard KL Distillation
165.
Progressive Distillation
166.
Ensemble Distillation
167.
Distillation Checkpoint
168.
Average Merge
169.
Weighted Merge
170.
SLERP Merge
171.
TIES Merge
172.
DARE Merge
173.
Hierarchical Merge
174.
Int4 Quantization
175.
Fake QAT
176.
Tune
Category S: Chat Templates
177.
Overview
178.
ChatML Format
179.
LLaMA 2 Format
180.
Mistral Format
181.
Multi-Format Detection
182.
Injection Defense
Category T: Model Analysis
183.
Overview
184.
Inspect
185.
Validate
186.
Diff
187.
Bench
188.
Profile
189.
QA Gates
190.
Oracle
191.
Canary
192.
Tree
193.
Hex
194.
Explain
195.
Trace
196.
Eval
197.
Flow
198.
Lint
199.
Check
200.
Debug
201.
Parity
202.
Qualify
203.
Compare HuggingFace
204.
Probar
205.
Tensors
206.
Slice
207.
QA Capability
208.
Model Fingerprint
Category U: Format Operations
209.
Overview
210.
Import from HuggingFace
211.
Export SafeTensors
212.
Export GGUF
213.
Rosetta Convert
214.
Rosetta Chain
215.
Rosetta Verify
216.
Convert + Quantize
217.
Publish
218.
Pull + Cache
219.
Batch Export
220.
Migration Pipeline
Category V: Advanced Pipelines
221.
Overview
222.
Model Showcase
223.
CI/CD Pipeline
224.
A/B Experiment
225.
Debug-Fix Loop
226.
Compliance Audit
Category Y: Acceleration
227.
Overview
228.
Autotuner
229.
Kernel Fusion
230.
Memory-Mapped Inference
231.
Quantized MatMul
232.
Compression Benchmark
233.
Cache Tiling
Deployment Stacks
234.
Overview
235.
Recipes
235.1.
alimentar-ingest
235.2.
apr-inference-server
235.3.
batuta-agent
235.4.
entrenar-train
235.5.
jetson-edge-base
235.6.
pacha-registry
235.7.
pepita-sandbox
235.8.
realizar-serve
235.9.
renacer-observability
235.10.
repartir-worker
235.11.
sovereign-ai-stack
235.12.
trueno-db-analytics
235.13.
trueno-rag-pipeline
235.14.
whisper-apr-asr
236.
Stacks
236.1.
01 Inference
236.2.
02 Training
236.3.
03 RAG
236.4.
04 Speech
236.5.
05 Distributed Inference
236.6.
06 Full Stack
236.7.
07 Data Pipeline
236.8.
08 Observability
236.9.
09 Edge Inference
236.10.
10 Qwen-Coder
237.
Machines
237.1.
Jetson
238.
forjar Integration
Data Loading
239.
Introduction
240.
Architecture
240.1.
Design Principles
240.2.
Module Structure
241.
Dataset
241.1.
Arrow Dataset
241.2.
CSV Files
241.3.
JSON Files
241.4.
Parquet Files
241.5.
Streaming
241.6.
Operations
242.
DataLoader
242.1.
Batching
242.2.
Shuffling
242.3.
Drop-Last
242.4.
Iteration Patterns
243.
Datasets Catalog
243.1.
MNIST
243.2.
Fashion-MNIST
243.3.
CIFAR-10
243.4.
CIFAR-100
243.5.
Iris
244.
Backends
244.1.
Local
244.2.
Memory
244.3.
HTTP
244.4.
S3
245.
Transforms
245.1.
Built-in
245.2.
Filter
245.3.
Map
245.4.
Cast
245.5.
Normalize
245.6.
Drop
245.7.
Select
245.8.
Rename
245.9.
Sample
245.10.
Shuffle
245.11.
Sort
245.12.
Take/Skip
245.13.
Unique
245.14.
Fill Null
245.15.
Chaining
245.16.
Custom Transforms
246.
HuggingFace Hub
246.1.
Importing
246.2.
Publishing
246.3.
Cache
246.4.
API Reference
247.
CLI Reference
247.1.
convert
247.2.
schema
247.3.
head
247.4.
view
247.5.
info
247.6.
registry
248.
Examples
248.1.
Basic Loading
248.2.
DataLoader Batching
248.3.
Transforms Pipeline
248.4.
Streaming Memory
248.5.
Quality Validation
248.6.
Drift Detection
248.7.
Federated Splitting
248.8.
HuggingFace Hub
248.9.
CLI/REPL
248.10.
Edge Cases / WASM
249.
Appendix
249.1.
Migration Guide
249.2.
FAQ
249.3.
Changelog
Visualization
250.
Introduction
251.
Getting Started
251.1.
Installation
251.2.
Core Concepts
251.3.
First App
251.4.
YAML Configuration
252.
Architecture
252.1.
Widget Tree
252.2.
Layer Hierarchy
252.3.
Rendering Pipeline
252.4.
Layout Engine
252.5.
Data Flow
252.6.
State Management
252.7.
Event System
253.
Layout System
253.1.
Constraints
253.2.
Flexbox Model
253.3.
Grid System
253.4.
Responsive Design
253.5.
Layout Caching
254.
Examples
254.1.
Charts
254.2.
Dashboard
254.3.
Data Table
254.4.
Counter App
254.5.
Data Management
254.6.
MNIST Explorer
254.7.
Model Card Display
254.8.
Shell Autocomplete
254.9.
Fraud Detection
254.10.
Edge Cases
255.
Quality
255.1.
Accessibility Metrics
255.2.
App Quality Score
255.3.
Data Quality Metrics
255.4.
Performance Metrics
255.5.
Structural Metrics
255.6.
Grade Thresholds
256.
Advanced
256.1.
GPU Rendering
256.2.
WGSL Shaders
256.3.
Anti-Aliasing
256.4.
Memory Management
256.5.
Virtualization
256.6.
Bundle Size
256.7.
WASM Optimization
257.
Appendix
257.1.
Migration Guide
257.2.
References
257.3.
WCAG Checklist
257.4.
FAQ
257.5.
Changelog
Code (apr code agentic surface)
258.
Overview
TSP (aprender-tsp)
259.
Overview
Shell (aprender-shell)
260.
Overview
Monte Carlo (aprender-monte-carlo)
261.
Overview
CGP (aprender-cgp)
262.
Overview
Contracts Macros (aprender-contracts-macros)
263.
Overview
Reference
264.
API Documentation
265.
Error Handling
266.
Feature Flags
Appendix
267.
Toyota Way Principles
268.
Recipe QA Checklist
Light
Rust
Coal
Navy
Ayu
APR Cookbook - Idiomatic Rust Patterns for ML Model Deployment
Speculative Decoding
Speculative decoding for faster autoregressive generation.
cargo run --example speculative_decode