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 — full-stack AI/ML coding agent
- Leeroopedia MCP — knowledge search for any coding agent
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:Volcengine Verl Multi Turn Tool Use Training
- Workflow:Farama Foundation Gymnasium RL Agent Training Loop
- Workflow:Openai Openai python Chat Completion
- Workflow:Langgenius Dify Plugin Installation and Configuration
- Workflow:Ggml org Llama cpp Embedding Extraction
- Workflow:VainF Torch Pruning Object Detection Pruning
- Workflow:Dotnet Machinelearning Text Classification
- Workflow:Huggingface Transformers PEFT Adapter Integration
- Workflow:Vespa engine Vespa Document indexing pipeline
- Workflow:Helicone Helicone Integrate Provider To Gateway
Principles
- Principle:Apache Hudi Clustering Layout Analysis
- Principle:OpenRLHF OpenRLHF Rule Based Reward Functions
- Principle:Openai Openai python Fine Tuning Job Monitoring
- Principle:Google deepmind Dm control MJCF Structure Building
- Principle:EvolvingLMMs Lab Lmms eval Results Output
- Principle:Vllm project Vllm Output Schema Definition
- Principle:Huggingface Datasets Download Configuration
- Principle:Speechbrain Speechbrain Transducer ASR Training
- Principle:Allenai Open instruct DPO Loss Dispatch
- Principle:Huggingface Open r1 Environment Setup
Implementations
- Implementation:Eventual Inc Daft Session Sql
- Implementation:Langgenius Dify UpdateAppSiteStatus
- Implementation:Bentoml BentoML Buildah Backend
- Implementation:Online ml River Preprocessing OrdinalEncoder
- Implementation:Run llama Llama index EvaluationResult Analysis
- Implementation:Online ml River Tree Splitter NominalReg
- Implementation:TobikoData Sqlmesh ModelNodeHeaderHandles
- Implementation:Helicone Helicone Alert Types
- Implementation:Iamhankai Forest of Thought CoT Task Run
- Implementation:Apache Shardingsphere VersionPersistService SwitchActiveVersion
Heuristics
- Heuristic:OpenRLHF OpenRLHF vLLM Embedding Resize Warning
- Heuristic:Sgl project Sglang Chunked Prefill OOM Prevention
- Heuristic:Fastai Fastbook Discriminative Learning Rates
- Heuristic:Scikit learn Scikit learn Feature Scaling Numerical Stability
- Heuristic:AnswerDotAI RAGatouille In Memory Reranking Limits
- Heuristic:Romsto Speculative Decoding Seed Fixing For Reproducibility
- Heuristic:Puppeteer Puppeteer Chrome Default Launch Arguments
- Heuristic:Apache Beam Warning Deprecated Twister2 Runner
- Heuristic:Google deepmind Mujoco Mesh Quality For Collision
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
Environments
- Environment:Tensorflow Serving Python Client Environment
- Environment:Vibrantlabsai Ragas LLM Provider Credentials
- Environment:Hiyouga LLaMA Factory Quantization Dependencies
- Environment:Mistralai Client python Agents Environment
- Environment:Openai Whisper Numba
- Environment:TobikoData Sqlmesh Dbt Compatibility
- Environment:Pyro ppl Pyro Funsor Backend
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:Obss Sahi Python Image Processing
- Environment:Apache Kafka Committer Tools Environment