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:Langchain ai Langgraph Functional API Workflow
- Workflow:PrefectHQ Prefect Database Cleanup With Approval
- Workflow:Huggingface Alignment handbook Multi Stage Post Training
- Workflow:Truera Trulens Snowflake Observability Pipeline
- Workflow:Facebookresearch Habitat lab PointNav PPO Training
- Workflow:Openai Openai node Streaming To Client
- Workflow:Sktime Pytorch forecasting TFT Hyperparameter Optimization
- Workflow:Mage ai Mage ai Destination Data Loading
- Workflow:FlowiseAI Flowise Evaluation Pipeline
- Workflow:Intel Ipex llm vLLM Serving
Principles
- Principle:Vespa engine Vespa Control File Initialization
- Principle:Helicone Helicone Cross Provider Transform
- Principle:PrefectHQ Prefect Dbt Project Setup
- Principle:Pyro ppl Pyro Markov Dependency
- Principle:Facebookresearch Audiocraft Finetuning Checkpoint Preparation
- Principle:Ggml org Llama cpp GGUFFormat
- Principle:Interpretml Interpret EBM JSON Serialization
- Principle:Fastai Fastbook Latent Factor Model
- Principle:Kserve Kserve Authentication Integration
- Principle:Vllm project Vllm OpenAI Client Integration
Implementations
- Implementation:Predibase Lorax Lorax Launcher Main
- Implementation:Ggml org Llama cpp GGUF Example
- Implementation:Haosulab ManiSkill AssemblingKits
- Implementation:Ollama Ollama MLXRunner Server
- Implementation:Googleapis Python genai Models Edit Image
- Implementation:Shiyu coder Kronos CustomKlineDataset Usage
- Implementation:Apache Paimon RowKind Python
- Implementation:Puppeteer Puppeteer NodeWebSocketTransport
- Implementation:SeleniumHQ Selenium UnpinnedScriptKey
- Implementation:Mlc ai Mlc llm OpenAIProtocol Kotlin
Heuristics
- Heuristic:Duckdb Duckdb Unity Build Strategy
- Heuristic:Togethercomputer Together python Multipart Upload Strategy
- Heuristic:Norrrrrrr lyn WAInjectBench Zero Vector Fallback Failed Embeddings
- Heuristic:Run llama Llama index Finetuning Warmup Steps
- Heuristic:Isaac sim IsaacGymEnvs Determinism Performance Tradeoff
- Heuristic:Datahub project Datahub Batch Size And Timeout Tuning
- Heuristic:Deepseek ai Janus Bfloat16 Dtype Selection
- Heuristic:Trailofbits Fickling Force Flag Bypass
- Heuristic:Sgl project Sglang Memory Fraction Tuning
- Heuristic:Turboderp org Exllamav2 Memory Optimization Techniques
Environments
- Environment:Astronomer Astronomer cosmos Cosmos Airflow Configuration
- Environment:Dagster io Dagster Python 3 10 Runtime
- Environment:Pyro ppl Pyro Distributed Training
- Environment:VainF Torch Pruning LLM Pruning Dependencies
- Environment:TobikoData Sqlmesh Snowflake Connection
- Environment:Mbzuai oryx Awesome LLM Post training Git CLI
- Environment:Huggingface Trl Quantization Environment
- Environment:Snorkel team Snorkel SpaCy NLP
- Environment:ThreeSR Awesome Inference Time Scaling Python Runtime Environment
- Environment:Astronomer Astronomer cosmos Python Airflow Runtime