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:ARISE Initiative Robosuite Teleoperation
- Workflow:Anthropics Anthropic sdk python Extended Thinking Reasoning
- Workflow:Neuml Txtai RAG Pipeline
- Workflow:Apache Flink Async Sink Lifecycle
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:Openai Whisper Word Level Timestamps
- Workflow:Webdriverio Webdriverio Cucumber BDD Testing
- Workflow:Ggml org Llama cpp Model Perplexity Evaluation
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:FlagOpen FlagEmbedding Embedder Inference
Principles
- Principle:Datajuicer Data juicer Data Format Loading
- Principle:Eventual Inc Daft List Explosion
- Principle:Sktime Pytorch forecasting Point Loss Functions
- Principle:Deepset ai Haystack Document Writing
- Principle:Helicone Helicone Environment Configuration
- Principle:Spotify Luigi HDFS Data Sources
- Principle:Intel Ipex llm Serving Benchmark Methodology
- Principle:Huggingface Datatrove Duplicate Removal
- Principle:Avhz RustQuant Interpolation
- Principle:Ollama Ollama HardwareDiscovery
Implementations
- Implementation:Ucbepic Docetl SemanticAccessor Usage
- Implementation:NVIDIA TransformerEngine Ops L2Normalization
- Implementation:Mit han lab Llm awq LLaVA Image Processing
- Implementation:Ollama Ollama Mtmd GLM4V
- Implementation:Explodinggradients Ragas BaseRagasEmbedding Class
- Implementation:ChenghaoMou Text dedup Bloom Filter Func
- Implementation:Protectai Llm guard Output ReadingTime
- Implementation:Spotify Luigi ExternalDailySnapshot
- Implementation:Apache Paimon MathUtils
- Implementation:Ggml org Ggml Quants api
Heuristics
- Heuristic:Kubeflow Pipelines Resource Sizing For Components
- Heuristic:Apache Druid Auto Granularity Selection
- Heuristic:Iamhankai Forest of Thought Early Stop Majority Vote
- Heuristic:Openai Openai agents python GPT 5 Reasoning Settings
- Heuristic:Tensorflow Serving Batching Thread Tuning
- Heuristic:Testtimescaling Testtimescaling github io Dual JSON Sync
- Heuristic:OpenGVLab InternVL Packed Training Buffer Management
- Heuristic:Apache Spark Hardware Provisioning Tips
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
Environments
- Environment:Online ml River Python Runtime Environment
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Apache Dolphinscheduler Database Backend
- Environment:Astronomer Astronomer cosmos Cosmos Airflow Configuration
- Environment:Open compass VLMEvalKit GPU CUDA Environment
- Environment:Webdriverio Webdriverio Cloud Service Credentials
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:Evidentlyai Evidently SQL Storage Environment