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:Sgl project Sglang Structured Output Generation
- Workflow:AnswerDotAI RAGatouille ColBERT Training
- Workflow:LaurentMazare Tch rs Transfer Learning
- Workflow:Google deepmind Dm control Multi Agent Soccer Setup
- Workflow:Microsoft Playwright Trace recording and debugging
- Workflow:Huggingface Trl GRPO Training
- Workflow:Mage ai Mage ai SQL Database Source Extraction
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Zai org CogVideo Video Editing DDIM Inversion
- Workflow:Open compass VLMEvalKit API Model Evaluation
Principles
- Principle:Infiniflow Ragflow Document Upload
- Principle:Ggml org Llama cpp ModelArchitecture
- Principle:Eventual Inc Daft Row Wise UDF
- Principle:DataTalksClub Data engineering zoomcamp Data Deduplication
- Principle:Hpcaitech ColossalAI SFT Model Loading
- Principle:InternLM Lmdeploy Engine Configuration
- Principle:Ggml org Llama cpp KVCache
- Principle:OWASP Www project top 10 for large language model applications Red Team Results Analysis
- Principle:Ggml org Llama cpp Performance
- Principle:PacktPublishing LLM Engineers Handbook LLM As Judge Evaluation
Implementations
- Implementation:Apache Paimon PagedList
- Implementation:Microsoft Playwright PageAgentDispatcher
- Implementation:Avhz RustQuant Heston Backend
- Implementation:Huggingface Transformers Create Packed Sequences
- Implementation:Iterative Dvc Repo Diff
- Implementation:Rapidsai Cuml SMO Solver
- Implementation:CarperAI Trlx NeMo PPO Model
- Implementation:SeleniumHQ Selenium Closure UI ControlRenderer
- Implementation:FlagOpen FlagEmbedding LLM Embedder Eval ICL
- Implementation:Avhz RustQuant Python Bindings
Heuristics
- Heuristic:Neuml Txtai Llama Cpp Context Fallback
- Heuristic:Mlc ai Mlc llm OpenCL Memory Floor Workaround
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:Microsoft Onnxruntime Graph Optimization Level Selection
- Heuristic:Apache Beam Watermark Update Throttling
- Heuristic:Alibaba MNN Backend Selection Guide
- Heuristic:Kornia Kornia Avoid Inplace Ops Compile
- Heuristic:Huggingface Diffusers VAE Scaling Factors
- Heuristic:PacktPublishing LLM Engineers Handbook Dataset Generation Quality Filters
- Heuristic:Romsto Speculative Decoding Ngram Order Selection
Environments
- Environment:OpenRLHF OpenRLHF DeepSpeed Environment
- Environment:LMCache LMCache CUDA GPU Runtime
- Environment:MarketSquare Robotframework browser Docker Container
- Environment:Eric mitchell Direct preference optimization HuggingFace Transformers
- Environment:Huggingface Datasets Python PyArrow Core
- Environment:Langchain ai Langchain OpenAI API Credentials
- Environment:Gretelai Gretel synthetics Python Base Environment
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Apache Druid Druid Operator Kubernetes
- Environment:Huggingface Transformers 3D Parallel Multi GPU