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:Nightwatchjs Nightwatch Programmatic API Usage
- Workflow:Zai org CogVideo Video Captioning
- Workflow:FMInference FlexLLMGen Data Wrangling Batch Inference
- Workflow:InternLM Lmdeploy LLM API Server Deployment
- Workflow:Nautechsystems Nautilus trader Live trading deployment
- Workflow:Google deepmind Mujoco Model compilation and conversion
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:Dagster io Dagster Modal Serverless Pipeline
- Workflow:NVIDIA NeMo Curator Video Curation Pipeline
- Workflow:Huggingface Trl Reward Model Training
Principles
- Principle:LaurentMazare Tch rs Tensor Type Conversion
- Principle:SeleniumHQ Selenium Session Request Routing
- Principle:Anthropics Anthropic sdk python Response Processing
- Principle:Ggml org Llama cpp Batch Processing
- Principle:Open compass VLMEvalKit Video Dataset Configuration
- Principle:CarperAI Trlx ROUGE Evaluation
- Principle:Triton inference server Server API Access Restriction
- Principle:Avhz RustQuant SABR Volatility
- Principle:MarketSquare Robotframework browser Custom Keyword Invocation
- Principle:Alibaba MNN Continuous Integration Testing
Implementations
- Implementation:HKUDS AI Trader Agent Ainvoke
- Implementation:BerriAI Litellm Get Model Cost Map
- Implementation:Eventual Inc Daft Set Runner Ray
- Implementation:OpenGVLab InternVL InternVLChatModel From Pretrained
- Implementation:Mlc ai Web llm Completion Request
- Implementation:Princeton nlp Tree of thought llm Test Output
- Implementation:Apache Dolphinscheduler Clients Proxy Factory
- Implementation:Apache Paimon PartitionStatistics
- Implementation:Cypress io Cypress Reporter Component
- Implementation:Huggingface Diffusers Export To Video
Heuristics
- Heuristic:Iamhankai Forest of Thought Input Length Overflow Recovery
- Heuristic:BerriAI Litellm Token Counting Buffer
- Heuristic:Lance format Lance Warning Deprecated Legacy Encodings
- Heuristic:Huggingface Peft Warning Deprecated Bone
- Heuristic:CARLA simulator Carla Traffic Manager Sync Mode
- Heuristic:DataTalksClub Data engineering zoomcamp Dbt Materialization Strategy
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Test Train Option Consistency
- Heuristic:Mlc ai Web llm Multi Round KV Cache Reuse
- Heuristic:NVIDIA TransformerEngine Build Optimization Tips
- Heuristic:Tensorflow Tfjs WASM Cross Origin Isolation
Environments
- Environment:Sgl project Sglang Distributed
- Environment:Apache Airflow Development Contributor Environment
- Environment:SeleniumHQ Selenium Contributor Development Environment
- Environment:NVIDIA NeMo Aligner PyTriton Serving Environment
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Mage ai Mage ai Python 3 9 Runtime
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Marker Inc Korea AutoRAG Python 3 10 Runtime
- Environment:Alibaba ROLL DeepSpeed Training Environment
- Environment:Sgl project Sglang Kubernetes