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:Huggingface Alignment handbook SFT DPO Alignment Pipeline
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:Huggingface Trl Reward Model Training
- Workflow:Langchain ai Langchain Chat Model Invocation
- Workflow:Bitsandbytes foundation Bitsandbytes 8bit Optimizer Training
- Workflow:Deepset ai Haystack RAG Pipeline
- Workflow:Lance format Lance Full Text Search
- Workflow:Evidentlyai Evidently Text Data Quality Evaluation
- Workflow:Langgenius Dify Visual Workflow Builder
- Workflow:Pola rs Polars Time Series Analysis
Principles
- Principle:Ucbepic Docetl Entity Link Resolution
- Principle:Turboderp org Exllamav2 Batch Job Iteration
- Principle:Iamhankai Forest of Thought Expression Validation
- Principle:Open compass VLMEvalKit VLM Adapter Pattern
- Principle:Heibaiying BigData Notes HBase Coprocessor Observer
- Principle:Apache Paimon Global Index Scan Building
- Principle:Haosulab ManiSkill Environment Registration
- Principle:Run llama Llama index QA Pair Generation
- Principle:SqueezeAILab ETS ETS Tree Search
- Principle:Huggingface Diffusers Prior Preservation
Implementations
- Implementation:Openai Openai python Response Computer Tool Call Param
- Implementation:Google deepmind Mujoco Engine Solver
- Implementation:Microsoft Semantic kernel Kernel CreateBuilder
- Implementation:Microsoft Autogen Studio Eval Judges
- Implementation:Rapidsai Cuml MBSGDClassifier
- Implementation:Marker Inc Korea AutoRAG Make Basic Gen Gt
- Implementation:Apache Beam BeamBatchWorker Execute
- Implementation:Datahub project Datahub OpenLineageToDataHub ConvertRunEvent
- Implementation:Ggml org Ggml Metal impl
- Implementation:Avhz RustQuant ExchangeRate
Heuristics
- Heuristic:Apache Flink Hadoop Thread Safety Mutexes
- Heuristic:Apache Druid Cluster Health Diagnostic Thresholds
- Heuristic:SqueezeAILab ETS Embedding Model GPU Collocation
- Heuristic:Apache Spark Warning Deprecated DStream Streaming
- Heuristic:Teamcapybara Capybara Async Waiting And Retry
- Heuristic:Microsoft DeepSpeedExamples Gradient Checkpointing Tradeoff
- Heuristic:ContextualAI HALOs TF32 Matmul Acceleration
- Heuristic:Mlfoundations Open flamingo RICES Feature Caching
- Heuristic:Mlc ai Mlc llm Metal KV Cache Capacity Limit
- Heuristic:FlowiseAI Flowise Edge Connection Type Matching
Environments
- Environment:Tensorflow Tfjs Browser Runtime
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies
- Environment:Run llama Llama index OpenAI API Configuration
- Environment:Huggingface Datasets SQL Dependencies
- Environment:Pola rs Polars Python Runtime Environment
- Environment:Isaac sim IsaacGymEnvs IsaacGym Preview 4
- Environment:PacktPublishing LLM Engineers Handbook API Credentials
- Environment:SeleniumHQ Selenium Grid Deployment Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas
- Environment:Princeton nlp SimPO CUDA Training