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:TobikoData Sqlmesh Dbt project migration
- Workflow:Spotify Luigi Central Scheduler Deployment
- Workflow:DataTalksClub Data engineering zoomcamp Kestra ETL Pipeline
- Workflow:Ucbepic Docetl YAML Pipeline Execution
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:Microsoft Playwright Browser automation CLI
- Workflow:CARLA simulator Carla Sensor Data Collection
- Workflow:Openai Openai python Realtime Conversation
- Workflow:Datahub project Datahub Protobuf Schema Ingestion
- Workflow:NVIDIA NeMo Aligner DPO Training
Principles
- Principle:Google research Deduplicate text datasets Self Similar Duplicate Detection
- Principle:Ggml org Ggml Token Sampling
- Principle:Triton inference server Server Signal Handling
- Principle:Langfuse Langfuse OTel Ingestion Post Processing
- Principle:Mit han lab Llm awq Quantized Weight Loading
- Principle:Intel Ipex llm LLM Serving With FastAPI
- Principle:Deepset ai Haystack Document Data Model
- Principle:Apache Hudi Schema Change Planning
- Principle:Lm sys FastChat OpenAI Compatible API Serving
- Principle:Huggingface Diffusers Model Publishing
Implementations
- Implementation:Apache Flink SourceReaderOptions
- Implementation:Datajuicer Data juicer VideoTaggingFromAudioMapper
- Implementation:Sgl project Sglang Init Distributed Environment
- Implementation:Eventual Inc Daft DataFrame Write Deltalake
- Implementation:Open compass VLMEvalKit CGBench Utils
- Implementation:Microsoft Onnxruntime OrtProvider
- Implementation:Bentoml BentoML Spark Batch
- Implementation:FlowiseAI Flowise Swagger API Specification
- Implementation:LLMBook zh LLMBook zh github io FilterPassageByLangs Filter Single Text
- Implementation:Open compass VLMEvalKit QwenAPI
Heuristics
- Heuristic:Vibrantlabsai Ragas Temperature Sampling Strategy
- Heuristic:Cohere ai Cohere python Embed Auto Batching Strategy
- Heuristic:Elevenlabs Elevenlabs python VAD vs Manual Commit Strategy
- Heuristic:Zai org CogVideo Memory Optimization Strategies
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Apache Beam Lock Contention Batching
- Heuristic:Eric mitchell Direct preference optimization FSDP Mixed Precision BFloat16
- Heuristic:Romsto Speculative Decoding Shared Tokenizer Requirement
- Heuristic:Datahub project Datahub Validation Across All APIs
- Heuristic:Heibaiying BigData Notes Spark Streaming Local Threads Tip
Environments
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Guardrails ai Guardrails LLM Provider API Keys
- Environment:Microsoft Semantic kernel ONNX CUDA Environment
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Sktime Pytorch forecasting Core Python Dependencies
- Environment:Interpretml Interpret Blackbox Explainer Dependencies
- Environment:Openclaw Openclaw Gateway Network Ports
- Environment:Predibase Lorax Model Source Credentials
- Environment:OpenRLHF OpenRLHF CUDA GPU Environment