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:Lance format Lance Full Text Search
- Workflow:Langgenius Dify Knowledge Base Creation
- Workflow:Google deepmind Dm control Manipulation Task Setup
- Workflow:PacktPublishing LLM Engineers Handbook RAG Inference
- Workflow:Allenai Open instruct Reward Model Training
- Workflow:Nightwatchjs Nightwatch Page Object Pattern
- Workflow:OpenHands OpenHands Conversation Lifecycle Management
- Workflow:Spotify Luigi Database Ingestion Pipeline
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:Snorkel team Snorkel Weak Supervision Pipeline
Principles
- Principle:Ggml org Llama cpp HF to GGUF Conversion
- Principle:Turboderp org Exllamav2 Layer Normalization
- Principle:Pyro ppl Pyro MCMC Posterior Sampling
- Principle:Tensorflow Tfjs Weight Regularization
- Principle:OpenBMB UltraFeedback Prompt Formatting
- Principle:Online ml River Prediction Anomaly Detection
- Principle:Turboderp org Exllamav2 Prompt Format Templating
- Principle:Axolotl ai cloud Axolotl Configuration Validation
- Principle:Google deepmind Mujoco MJX Physics Stepping
- Principle:Alibaba ROLL Diffusion Model Preparation
Implementations
- Implementation:Langgenius Dify Init Permissions Container
- Implementation:FMInference FlexLLMGen DeepSpeed Runner
- Implementation:Apache Druid Ingestion Type Routing
- Implementation:Ucbepic Docetl WebSocket Run Pipeline
- Implementation:Vespa engine Vespa Container Disc ABI Spec
- Implementation:OWASP Www project top 10 for large language model applications VotingSystem Refine and Revote
- Implementation:Interpretml Interpret DetermineLinkFunction
- Implementation:Mbzuai oryx Awesome LLM Post training Matplotlib Bar Chart
- Implementation:ClickHouse ClickHouse Clickhouse Program Add Macro
- Implementation:CrewAIInc CrewAI Merge Agent Handler Tool
Heuristics
- Heuristic:FlowiseAI Flowise Edge Connection Type Matching
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:Iamhankai Forest of Thought Self Correction Confidence Threshold
- Heuristic:Fastai Fastbook Batch Size Selection
- Heuristic:Sail sg LongSpec NCCL Distributed Settings
- Heuristic:Anthropics Anthropic sdk python Retry Backoff Strategy
- Heuristic:Kornia Kornia Morphology Engine Selection
- Heuristic:Alibaba MNN NC4HW4 Data Layout
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Microsoft Agent framework Function Invocation Defaults
Environments
- Environment:Pyro ppl Pyro Funsor Backend
- Environment:Tensorflow Serving Build Environment
- Environment:Fede1024 Rust rdkafka Kafka Broker Runtime
- Environment:AnswerDotAI RAGatouille Python ColBERT Dependencies
- Environment:ThreeSR Awesome Inference Time Scaling Semantic Scholar API Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Ollama Ollama GPU Runtime
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Treeverse LakeFS Web UI Environment
- Environment:Promptfoo Promptfoo Node Runtime