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:Ucbepic Docetl Python API Pipeline
- Workflow:Huggingface Diffusers Video Generation
- Workflow:Groq Groq python Audio Transcription
- Workflow:Apache Druid SQL Query Execution
- Workflow:Guardrails ai Guardrails Streaming Validation
- Workflow:Haosulab ManiSkill Imitation Learning Pipeline
- Workflow:Hpcaitech ColossalAI LLaMA Continual Pretraining
- Workflow:OpenRLHF OpenRLHF PPO Ray Training
- Workflow:Google deepmind Dm control Control Suite RL Training
- Workflow:Onnx Onnx External Data Handling
Principles
- Principle:Ggml org Llama cpp CI Testing
- Principle:Spotify Luigi Dependency Analysis
- Principle:Open compass VLMEvalKit Video Dataset Configuration
- Principle:Fastai Fastbook Collab DataLoaders
- Principle:DistrictDataLabs Yellowbrick Residual Analysis
- Principle:Langfuse Langfuse Score Validation and Creation
- Principle:DistrictDataLabs Yellowbrick Manifold Embedding
- Principle:Pola rs Polars Expression Pipeline Building
- Principle:Diagram of thought Diagram of thought Final Synthesis
- Principle:Neuml Txtai Production Deployment
Implementations
- Implementation:Langfuse Langfuse Seeder Data Generators
- Implementation:Microsoft Autogen Studio Elicitation Dialog
- Implementation:Tencent Ncnn ParamDict
- Implementation:Infiniflow Ragflow GenerateButton Component
- Implementation:Datajuicer Data juicer VideoDurationFilter
- Implementation:Iterative Dvc Repo Artifacts
- Implementation:Langgenius Dify App Layout
- Implementation:Fede1024 Rust rdkafka BaseProducer Transactional Config
- Implementation:Vllm project Vllm Connections
- Implementation:Microsoft Playwright APIRequestContext Fetch
Heuristics
- Heuristic:AnswerDotAI RAGatouille Searcher Configuration By Collection Size
- Heuristic:Princeton nlp SimPO Multi Seed Diversity
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:ArroyoSystems Arroyo Checkpoint Interval Tuning
- Heuristic:Mlfoundations Open flamingo KV Cache Classification Optimization
- Heuristic:Hiyouga LLaMA Factory Gradient Checkpointing Memory Optimization
- Heuristic:Fede1024 Rust rdkafka Librdkafka Debug Logging
- Heuristic:ChenghaoMou Text dedup Bloom Filter Single Process
- Heuristic:Huggingface Optimum GPTQ Quantization Defaults
- Heuristic:Microsoft Onnxruntime Threading Configuration Tips
Environments
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:Farama Foundation Gymnasium Box2D Physics Backend
- Environment:Unstructured IO Unstructured Libmagic
- Environment:Nautechsystems Nautilus trader Asyncio Uvloop Event Loop
- Environment:Google deepmind Mujoco Python Bindings Environment
- Environment:Huggingface Diffusers PyTorch CUDA Runtime
- Environment:Bigscience workshop Petals Python Transformers
- Environment:Alibaba ROLL CUDA GPU Environment
- Environment:Openai Openai agents python LiteLLM Dependencies
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention