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:Spotify Luigi Database Ingestion Pipeline
- Workflow:Danijar Dreamerv3 Single Process Training
- Workflow:Alibaba ROLL Agentic RL Training Pipeline
- Workflow:EvolvingLMMs Lab Lmms eval Custom Model Integration
- Workflow:Openai Openai python Image Generation
- Workflow:Microsoft Autogen Graph Based Agent Orchestration
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Microsoft BIPIA White Box Defense Finetuning
- Workflow:Duckdb Duckdb Benchmark Execution
- Workflow:PacktPublishing LLM Engineers Handbook RAG Inference
Principles
- Principle:Tencent Ncnn Oriented Bounding Box Decoding
- Principle:Ggml org Llama cpp Multimodal Language Model Loading
- Principle:PrefectHQ Prefect Asset Materialization
- Principle:Truera Trulens Selector Based Data Extraction
- Principle:Apache Kafka Broker Logging Configuration
- Principle:Langfuse Langfuse Experiment Run Creation
- Principle:Microsoft LoRA GLUE Data Download
- Principle:Huggingface Datatrove Document Level Statistics
- Principle:Webdriverio Webdriverio Appium Service Lifecycle
- Principle:Langgenius Dify DependencyManagement
Implementations
- Implementation:Farama Foundation Gymnasium Make Vec
- Implementation:Deepspeedai DeepSpeed Evoformer GEMM Utils
- Implementation:Roboflow Rf detr ORT InferenceSession
- Implementation:CrewAIInc CrewAI Brave Search Tool
- Implementation:BerriAI Litellm App Crypto
- Implementation:Vllm project Vllm Quick Reduce
- Implementation:Online ml River Tree Splitter Random
- Implementation:Neuml Txtai NumPy ANN
- Implementation:Hiyouga LLaMA Factory Model Loader
- Implementation:Truera Trulens TruBot App
Heuristics
- Heuristic:Deepseek ai Janus Bfloat16 Dtype Selection
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Fede1024 Rust rdkafka Cooperative Rebalance Protocol
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Strategy Selection
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Image Size Multiple of Four
- Heuristic:Apache Spark Warning Deprecated DStream Streaming
- Heuristic:DevExpress Testcafe Window Resize Correction
- Heuristic:Explodinggradients Ragas Concurrency And Rate Limiting
- Heuristic:Lm sys FastChat GPU Memory Allocation Strategy
- Heuristic:MaterializeInc Materialize CI Retry Strategies
Environments
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Datahub project Datahub Java Build
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:Vibrantlabsai Ragas Python 3 9 Core Environment
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Arize ai Phoenix OpenTelemetry SDK
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:Cohere ai Cohere python Cohere API Credentials
- Environment:Astronomer Astronomer cosmos Cosmos Airflow Configuration
- Environment:Turboderp org Exllamav2 CUDA GPU Runtime