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:LLMBook zh LLMBook zh github io Data Preprocessing Pipeline
- Workflow:Langchain ai Langchain Streaming Responses
- Workflow:Openai Openai python Embeddings Generation
- Workflow:Shiyu coder Kronos Qlib Finetuning
- Workflow:Ggml org Llama cpp HF to GGUF Model Conversion
- Workflow:Fede1024 Rust rdkafka Produce Consume Roundtrip
- Workflow:PeterL1n BackgroundMattingV2 Video matting inference
- Workflow:FlowiseAI Flowise Document Store Ingestion
- Workflow:Mistralai Client python Chat Completion
- Workflow:Ray project Ray Actor Lifecycle Management
Principles
- Principle:PacktPublishing LLM Engineers Handbook Prompt Engineering For Dataset Generation
- Principle:Astronomer Astronomer cosmos Execution Configuration
- Principle:Avdvg InjectGuard Vector Store Construction
- Principle:Protectai Llm guard Output Scanner Factory Pattern
- Principle:Anthropics Anthropic sdk python Provider API Interaction
- Principle:Microsoft Autogen Agent Specialization
- Principle:Apache Shardingsphere In Memory Rule Rebuild
- Principle:SeleniumHQ Selenium CDP Session Management
- Principle:Microsoft Semantic kernel Event Routing
- Principle:LaurentMazare Tch rs Top K Prediction
Implementations
- Implementation:Openai Openai node Batches Resource
- Implementation:Dotnet Machinelearning TrialResult Properties
- Implementation:Hpcaitech ColossalAI Train RM Script
- Implementation:Ggml org Llama cpp Convert Llama2c To GGML
- Implementation:Ray project Ray Buildkite Aarch64 Pipeline
- Implementation:Run llama Llama index MetadataReplacementPostProcessor
- Implementation:Farama Foundation Gymnasium HumanoidStandupEnv V4
- Implementation:Helicone Helicone XAI Model Definitions
- Implementation:Sgl project Sglang LWS Prefill Node Manifest
- Implementation:Infiniflow Ragflow Log Utils
Heuristics
- Heuristic:MarketSquare Robotframework browser Shared Node Process For Parallel
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:OpenHands OpenHands Fail Open Rate Limiting
- Heuristic:Vespa engine Vespa Log Level Inheritance Polling
- Heuristic:Microsoft Onnxruntime ORTModule Wrapping Order
- Heuristic:Apache Airflow Task Idempotency Pattern
- Heuristic:Mlflow Mlflow Async Logging Best Practices
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:Scikit learn Scikit learn Random State Management
- Heuristic:Intel Ipex llm LoRA Target All Linear Layers
Environments
- Environment:Axolotl ai cloud Axolotl Multi GPU
- Environment:Promptfoo Promptfoo SQLite Database
- Environment:Deepspeedai DeepSpeed CPU Environment
- Environment:Shiyu coder Kronos Qlib Data Environment
- Environment:Openclaw Openclaw Docker Deployment Environment
- Environment:Apache Kafka Release Toolchain Environment
- Environment:ThreeSR Awesome Inference Time Scaling Git CLI Environment
- Environment:Google deepmind Dm control EGL Headless Rendering
- Environment:Dagster io Dagster GRPC Communication
- Environment:AUTOMATIC1111 Stable diffusion webui Python And PyTorch Runtime