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:Guardrails ai Guardrails Server Deployment
- Workflow:Sdv dev SDV Data quality evaluation
- Workflow:EvolvingLMMs Lab Lmms eval Server Mode Evaluation
- Workflow:Scikit learn Scikit learn Ensemble Model Building
- Workflow:Lance format Lance Table Optimization
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Entry Development
- Workflow:Getgauge Taiko Headless Browser Testing
- Workflow:SeldonIO Seldon core Production Monitoring Pipeline
- Workflow:Vllm project Vllm OpenAI Compatible Serving
- Workflow:Tencent Ncnn Post Training Quantization
Principles
- Principle:Apache Paimon Blob Descriptor Construction
- Principle:Turboderp org Exllamav2 Layer Quantization
- Principle:Apache Spark Programmatic Application Launch
- Principle:Sgl project Sglang Multimodal Prompt Construction
- Principle:Datajuicer Data juicer Data Aggregation
- Principle:Deepset ai Haystack Embedding Based Retrieval
- Principle:FlagOpen FlagEmbedding Evaluation Configuration
- Principle:Lm sys FastChat Causal LM Loading
- Principle:Microsoft LoRA Distributed LoRA Training
- Principle:Ollama Ollama CLIDisplay
Implementations
- Implementation:CARLA simulator Carla DebugShape
- Implementation:CrewAIInc CrewAI Code Docs Search Tool
- Implementation:Haosulab ManiSkill PDJointVelController
- Implementation:Triton inference server Server Ensemble Infer Request
- Implementation:Togethercomputer Together python Audio Speech Types
- Implementation:Datahub project Datahub Filter Tag Indexes
- Implementation:Open compass VLMEvalKit PhyX Utils
- Implementation:Apache Paimon VectorSearch Construction
- Implementation:Microsoft Agent framework Content To Function Approval Response
- Implementation:BerriAI Litellm Secret Manager Main
Heuristics
- Heuristic:Vibrantlabsai Ragas Reasoning Model Parameter Constraints
- Heuristic:Mlc ai Web llm Service Worker Keep Alive
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
- Heuristic:Guardrails ai Guardrails Async Vs Sync Validation Mode
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:DistrictDataLabs Yellowbrick Model Fitted State Detection
- Heuristic:SqueezeAILab ETS Embedding Model GPU Collocation
- Heuristic:NVIDIA DALI Memory Pool Tuning
- Heuristic:Danijar Dreamerv3 Replay Context Carry Init
- Heuristic:NVIDIA NeMo Curator Semantic Dedup Cluster Sizing
Environments
- Environment:Mistralai Client python Realtime Transcription Environment
- Environment:Recommenders team Recommenders Spark Environment
- Environment:MaterializeInc Materialize Kubernetes Helm Runtime
- Environment:Apache Spark Python Environment
- Environment:SqueezeAILab ETS Multi GPU Sglang Runtime
- Environment:Openai Openai agents python OpenAI API Credentials
- Environment:Microsoft DeepSpeedExamples RLHF Training Environment
- Environment:Axolotl ai cloud Axolotl Python Runtime
- Environment:Kserve Kserve Kubernetes Cluster
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference