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:Openai Openai node Streaming To Client
- Workflow:Truera Trulens Snowflake Observability Pipeline
- Workflow:DataTalksClub Data engineering zoomcamp Docker PostgreSQL Data Ingestion
- Workflow:Lance format Lance Dataset Lifecycle
- Workflow:Astronomer Astronomer cosmos Kubernetes dbt execution
- Workflow:Microsoft Agent framework Multi Agent Concurrent Orchestration
- Workflow:Google research Deduplicate text datasets Suffix array querying
- Workflow:TA Lib Ta lib python Candlestick Pattern Recognition
- Workflow:Ggml org Ggml Model Conversion And Quantization
- Workflow:AnswerDotAI RAGatouille ColBERT Training
Principles
- Principle:Google deepmind Mujoco MJX Benchmarking
- Principle:Rapidsai Cuml Data Preparation For Clustering
- Principle:Risingwavelabs Risingwave CDC Source Database Preparation
- Principle:Ggml org Llama cpp Backend Loading
- Principle:Unstructured IO Unstructured Golden File Regression Testing
- Principle:Ollama Ollama ML Backend Abstraction
- Principle:DistrictDataLabs Yellowbrick Cross Validation Scoring
- Principle:Eventual Inc Daft Data Ingestion HuggingFace
- Principle:Online ml River Page Hinkley Drift Detection
- Principle:Huggingface Datasets In Place Format Setting
Implementations
- Implementation:Openai Openai python Moderations Resource
- Implementation:Mlc ai Mlc llm Attach Logit Processor Pass
- Implementation:Openai Openai python Response Custom Tool Call Input Done
- Implementation:Mlc ai Mlc llm Compile
- Implementation:Haotian liu LLaVA Apply Delta
- Implementation:Neuml Txtai ExportTask
- Implementation:Ollama Ollama Readline History
- Implementation:Alibaba MNN Protobuf Map Type Handler H
- Implementation:ArroyoSystems Arroyo Updating Cache
- Implementation:Ggml org Ggml Backend impl interface
Heuristics
- Heuristic:ChenghaoMou Text dedup SimHash Optimization Ceiling
- Heuristic:Mlflow Mlflow Nested Run Organization
- Heuristic:Openclaw Openclaw Retry With Exponential Backoff
- Heuristic:Eric mitchell Direct preference optimization RMSprop Over Adam
- Heuristic:NVIDIA DALI Memory Pool Tuning
- Heuristic:PrefectHQ Prefect Retry Backoff Strategy
- Heuristic:Huggingface Open r1 vLLM GPU Allocation
- Heuristic:Norrrrrrr lyn WAInjectBench Zero Vector Fallback Failed Embeddings
- Heuristic:Avdvg InjectGuard Embedding Normalization Cosine Equivalence
- Heuristic:Lm sys FastChat Conversation Splitting Token Buffer
Environments
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Neuml Txtai GPU Accelerator Environment
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Spotify Luigi Python Runtime
- Environment:Pyro ppl Pyro Funsor Backend
- Environment:Roboflow Rf detr Roboflow Deployment Credentials
- Environment:Openai Openai node Node 20 Runtime
- Environment:Anthropics Anthropic sdk python Azure Foundry Environment
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment
- Environment:Lm sys FastChat LoRA QLoRA Training Environment