Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Datajuicer Data juicer LLM Powered Data Generation
- Workflow:Google research Deduplicate text datasets Wiki40B TFDS deduplication
- Workflow:Mlflow Mlflow Prompt Management
- Workflow:SqueezeAILab ETS Answer Evaluation Pipeline
- Workflow:Apache Flink Async Sink Lifecycle
- Workflow:NVIDIA NeMo Curator Image Curation Pipeline
- Workflow:Diagram of thought Diagram of thought DoT Trace Extraction
- Workflow:PrefectHQ Prefect API Sourced ETL
- Workflow:Turboderp org Exllamav2 Interactive Chat
- Workflow:Getgauge Taiko Network Request Interception
Principles
- Principle:Nightwatchjs Nightwatch Cucumber Test Execution
- Principle:Apache Kafka Coordinator State Loading
- Principle:Haosulab ManiSkill Domain Randomization
- Principle:Volcengine Verl Reward Model Scoring
- Principle:Unslothai Unsloth MoE Expert Routing
- Principle:Dagster io Dagster Data Quality Validation
- Principle:Facebookresearch Audiocraft Flow Matching Generation
- Principle:ARISE Initiative Robosuite Placement Sampling
- Principle:DataTalksClub Data engineering zoomcamp Dbt Marts Layer
- Principle:OpenHands OpenHands Webhook Acknowledgment
Implementations
- Implementation:Lance format Lance LegacyListEncoding
- Implementation:Google deepmind Dm control Walker Rescale
- Implementation:OWASP Www project top 10 for large language model applications VulnerabilityEntry Parse Sections
- Implementation:ArroyoSystems Arroyo Nexmark Connector
- Implementation:FlowiseAI Flowise PromptLangsmithHubDialog
- Implementation:Datahub project Datahub RestEmitterConfig
- Implementation:Kserve Kserve Knative Traffic Reconciler
- Implementation:Haosulab ManiSkill Evaluate Dense Reward
- Implementation:Onnx Onnx Convert Model To External Data
- Implementation:Google deepmind Mujoco Engine Global Table
Heuristics
- Heuristic:Lm sys FastChat Conversation Splitting Token Buffer
- Heuristic:Microsoft LoRA Selective LoRA QV Only
- Heuristic:Dotnet Machinelearning Numerical Stability Guards
- Heuristic:Mlc ai Web llm Tokenizer JSON Preference
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:Mlc ai Mlc llm OpenCL Memory Floor Workaround
- Heuristic:Intel Ipex llm LoRA Target All Linear Layers
- Heuristic:Openai Openai python Retry Backoff Strategy
- Heuristic:Liu00222 Open Prompt Injection BPE Retokenization Parameters
- Heuristic:Pola rs Polars Lazy Over Eager Preference
Environments
- Environment:Microsoft Onnxruntime Windows Build Environment
- Environment:Openai CLIP PyTorch CUDA Runtime
- Environment:Iamhankai Forest of Thought OpenAI API Credentials
- Environment:Marker Inc Korea AutoRAG Japanese NLP Dependencies
- Environment:Snorkel team Snorkel PyTorch
- Environment:OpenRLHF OpenRLHF Ray Distributed Environment
- Environment:Kserve Kserve Knative Serving
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Bitsandbytes foundation Bitsandbytes Build From Source Environment
- Environment:Langgenius Dify Credentials And Env Vars