Main Page
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:Openai Evals Creating a model graded eval
- Workflow:Guardrails ai Guardrails Streaming Validation
- Workflow:Apache Druid Batch Data Ingestion
- Workflow:Google research Deduplicate text datasets Suffix array querying
- Workflow:LaurentMazare Tch rs LLM Text Generation
- Workflow:Langgenius Dify Application Creation
- Workflow:Langgenius Dify App Creation and Configuration
- Workflow:Webdriverio Webdriverio Standalone Browser Automation
- Workflow:LLMBook zh LLMBook zh github io Inference and Quantization
- Workflow:Kubeflow Pipelines XGBoost Training Pipeline
Principles
- Principle:Neuml Txtai Custom Function Tools
- Principle:LMCache LMCache Disaggregated Prefill Prerequisites
- Principle:Langgenius Dify App Type Selection
- Principle:VainF Torch Pruning BN Scale Regularization
- Principle:Groq Groq python Speech Request Configuration
- Principle:Isaac sim IsaacGymEnvs ADR State Checkpointing
- Principle:Online ml River Anomaly Scoring Interface
- Principle:Open compass VLMEvalKit Model Registration
- Principle:OpenGVLab InternVL Mixed Preference Optimization
- Principle:Norrrrrrr lyn WAInjectBench Training Data Loading
Implementations
- Implementation:Ggml org Llama cpp Llama Get Embeddings
- Implementation:Nautechsystems Nautilus trader StrategyConfig Definition
- Implementation:Huggingface Diffusers Enable Model Cpu Offload
- Implementation:Openai Openai agents python Codex Same Thread Pattern
- Implementation:OpenGVLab InternVL Concat Pad Data Collator
- Implementation:ArroyoSystems Arroyo State Core
- Implementation:ClickHouse ClickHouse Defines
- Implementation:Duckdb Duckdb FastPForLib
- Implementation:Fede1024 Rust rdkafka StreamConsumer Stream
- Implementation:Togethercomputer Together python Endpoints Resource
Heuristics
- Heuristic:Langfuse Langfuse LLM Rate Limit 24h Abandon
- Heuristic:Elevenlabs Elevenlabs python Text Chunking Splitter Characters
- Heuristic:Mage ai Mage ai Sorted Data Bookmark Strategy
- Heuristic:DataExpert io Data engineer handbook Flink Checkpointing Interval Tuning
- Heuristic:HKUDS AI Trader Market Type Auto Detection
- Heuristic:Microsoft Autogen Warning Deprecated JSON Env Files
- Heuristic:Axolotl ai cloud Axolotl Gradient Checkpointing Reentrant Rules
- Heuristic:SeleniumHQ Selenium Cross Binding Consistency Check
- Heuristic:Fastai Fastbook Dropout Regularization
- Heuristic:Microsoft DeepSpeedExamples ZeRO Inference Throughput Tuning
Environments
- Environment:DataExpert io Data engineer handbook Flink Kafka Docker Environment
- Environment:Farama Foundation Gymnasium MuJoCo Physics Backend
- Environment:Huggingface Optimum GPTQ Quantization Environment
- Environment:Getgauge Taiko Linux System Libraries
- Environment:Astronomer Astronomer cosmos Python Airflow Runtime
- Environment:Zai org CogVideo SAT Framework Environment
- Environment:Openai Openai agents python Voice Dependencies
- Environment:TobikoData Sqlmesh Python Runtime
- Environment:Pola rs Polars GPU Execution Environment
- Environment:PacktPublishing LLM Engineers Handbook Selenium Chrome Crawler Environment