Main Page
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:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Lakeraai Pint benchmark Custom Dataset Benchmarking
- Workflow:Explodinggradients Ragas Metric Prompt Optimization
- Workflow:Openai Openai node Chat Completion
- Workflow:Junyanz Pytorch CycleGAN and pix2pix CycleGAN Training
- Workflow:Huggingface Datasets Format Conversion
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:CrewAIInc CrewAI Sequential Crew Execution
- Workflow:Teamcapybara Capybara Custom Selector Definition
- Workflow:TA Lib Ta lib python Candlestick Pattern Recognition
Principles
- Principle:Scikit learn Scikit learn Gradient Boosting Classification
- Principle:Huggingface Datatrove Pipeline Step Abstraction
- Principle:Sail sg LongSpec Data Preparation
- Principle:Pola rs Polars Input Data Preparation
- Principle:ArroyoSystems Arroyo Two Phase Commit
- Principle:Openclaw Openclaw Extension Type Identification
- Principle:Datajuicer Data juicer Statistics Computation
- Principle:Ggml org Ggml CPU Feature Detection
- Principle:Sgl project Sglang Engine Initialization
- Principle:Mlc ai Web llm Tool Call Extraction
Implementations
- Implementation:Alibaba ROLL AutoConfig
- Implementation:NVIDIA NeMo Curator Wikipedia Downloader
- Implementation:Togethercomputer Together python CLI Main Entry
- Implementation:Infiniflow Ragflow ChunkCard Component
- Implementation:Vespa engine Vespa KStemmer Stem
- Implementation:Triton inference server Server L0 Cuda Graph Test
- Implementation:Explodinggradients Ragas CacheInterface And DiskCacheBackend
- Implementation:BerriAI Litellm Caching Handler
- Implementation:Mit han lab Llm awq Serve Controller
- Implementation:Getgauge Taiko Gauge Env Properties
Heuristics
- Heuristic:Nautechsystems Nautilus trader Order Rate Limiting Configuration
- Heuristic:Openai Openai python Streaming Resource Management
- Heuristic:Langchain ai Langchain Deprecation Version Tracking
- Heuristic:Pyro ppl Pyro MCMC Warmup Adaptation
- Heuristic:Sktime Pytorch forecasting Encoder Decoder Length Limits
- Heuristic:Run llama Llama index Evaluator LLM Selection
- Heuristic:Liu00222 Open Prompt Injection Defense Strategy Selection
- Heuristic:ContextualAI HALOs TF32 Matmul Acceleration
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:DistrictDataLabs Yellowbrick Scikit Learn API Compatibility
Environments
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:OWASP Www project top 10 for large language model applications Pre Commit Hooks Environment
- Environment:SeldonIO Seldon core Kafka Messaging Environment
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Helicone Helicone Wrangler CLI
- Environment:Iterative Dvc Git SCM Environment
- Environment:Snorkel team Snorkel SpaCy NLP
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Duckdb Duckdb Extension Distribution Env
- Environment:Openai Openai node OpenAI API Credentials