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:OpenBMB UltraFeedback Dataset Construction
- Workflow:Microsoft Agent framework Multi Agent Sequential Orchestration
- Workflow:Onnx Onnx Model Creation
- Workflow:VainF Torch Pruning LLM Structural Pruning
- Workflow:Ggml org Llama cpp Interactive Chat
- Workflow:OpenRLHF OpenRLHF PPO Ray Training
- Workflow:Ggml org Ggml GPT2 Text Generation
- Workflow:Ggml org Llama cpp Model Quantization
- Workflow:Mlfoundations Open flamingo Few Shot Evaluation
- Workflow:Mlfoundations Open flamingo Distributed Training
Principles
- Principle:Testtimescaling Testtimescaling github io Automated Git Commit
- Principle:Tencent Ncnn Top K Classification
- Principle:Cohere ai Cohere python Finetuning Configuration
- Principle:Arize ai Phoenix Batch Span Annotation
- Principle:Kserve Kserve CRD Schema Validation
- Principle:Open compass VLMEvalKit Video Dataset Configuration
- Principle:Openai Openai agents python Tool Execution Loop
- Principle:Mistralai Client python Finetuning Job Control
- Principle:Online ml River Streaming Statistics
- Principle:Huggingface Datasets Lance Dataset Building
Implementations
- Implementation:CrewAIInc CrewAI Platform Action Tool
- Implementation:Openai Openai python Container Retrieve Response
- Implementation:Pola rs Polars SQLContext Register
- Implementation:Explodinggradients Ragas Llm Factory
- Implementation:OWASP Www project top 10 for large language model applications EntryTranslator Translate
- Implementation:Google deepmind Mujoco WASM Functions Generator
- Implementation:Openai Openai node Node ESM Lockfile
- Implementation:Online ml River Evaluate Iter Progressive Val Score
- Implementation:Hiyouga LLaMA Factory Misc Utils
- Implementation:Elevenlabs Elevenlabs python ForcedAlignmentClient
Heuristics
- Heuristic:Farama Foundation Gymnasium Seeding Determinism Best Practices
- Heuristic:Facebookresearch Habitat lab VER Tuning Guidelines
- Heuristic:Huggingface Datatrove Gopher Quality Thresholds
- Heuristic:Pytorch Serve Ampere Tensor Core Optimization
- Heuristic:Isaac sim IsaacGymEnvs Determinism Performance Tradeoff
- Heuristic:Unslothai Unsloth Gradient Accumulation Accuracy
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Langchain ai Langgraph Recursion Limit Tuning
- Heuristic:PeterL1n BackgroundMattingV2 Data Augmentation Strategy
- Heuristic:Bitsandbytes foundation Bitsandbytes Compute Dtype Mismatch Warning
Environments
- Environment:Spotify Luigi Python Runtime
- Environment:Protectai Modelscan H5py Optional
- Environment:Sgl project Sglang CUDA SM100
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:Deepspeedai DeepSpeed XPU Environment
- Environment:Volcengine Verl CUDA GPU Environment
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:DevExpress Testcafe Node Runtime
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Bitsandbytes foundation Bitsandbytes HPU Gaudi Runtime