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:Rapidsai Cuml GPU Clustering
- Workflow:Nautechsystems Nautilus trader Data loading and cataloging
- Workflow:Sgl project Sglang ModelOpt Quantization And Export
- Workflow:Avhz RustQuant Model Calibration
- Workflow:Princeton nlp Tree of thought llm ToT BFS experiment
- Workflow:Truera Trulens RAG With Guardrails
- Workflow:Microsoft BIPIA Attack Success Rate Evaluation
- Workflow:Run llama Llama index Embedding Finetuning
- Workflow:Microsoft Semantic kernel Process Orchestration
- Workflow:LLMBook zh LLMBook zh github io LoRA Finetuning
Principles
- Principle:Triton inference server Server Performance Analysis
- Principle:Diagram of thought Diagram of thought Iterative Propose and Critique
- Principle:LMCache LMCache Worker Registration
- Principle:Dagster io Dagster Rate Limiting Strategy
- Principle:VainF Torch Pruning Group Norm Regularization
- Principle:Snorkel team Snorkel Labeling Function Analysis
- Principle:Huggingface Datasets Text Dataset Building
- Principle:Haosulab ManiSkill Physics Struct Abstraction
- Principle:Norrrrrrr lyn WAInjectBench Checkpoint Export
- Principle:Microsoft Autogen Swarm Orchestration
Implementations
- Implementation:Pytorch Serve Custom Sphinx Directives
- Implementation:Triton inference server Server AddCopyright
- Implementation:Explodinggradients Ragas Collections CHRFScore Metric
- Implementation:Langchain ai Langgraph AsyncSqliteSaver
- Implementation:Helicone Helicone Mitmproxy Mac
- Implementation:Ucbepic Docetl Blocking Utils
- Implementation:Infiniflow Ragflow UseAgentHistoryManager
- Implementation:Ollama Ollama Mtmd MiniCPMV
- Implementation:CrewAIInc CrewAI RAG JSON Loader
- Implementation:Googleapis Python genai CreateTuningJobConfig Setup
Heuristics
- Heuristic:Princeton nlp Tree of thought llm Value Caching
- Heuristic:CARLA simulator Carla Client Server Version Match
- Heuristic:SeldonIO Seldon core Autoscaling Dual Config Tip
- Heuristic:DataTalksClub Data engineering zoomcamp Dbt Materialization Strategy
- Heuristic:Apache Dolphinscheduler Netty Thread Sizing
- Heuristic:Allenai Open instruct Polyak Reference Update
- Heuristic:Open compass VLMEvalKit Judge Model Selection By Dataset
- Heuristic:Bentoml BentoML Platform Serving Caveats
- Heuristic:Trailofbits Fickling Severity Threshold Selection
- Heuristic:SeleniumHQ Selenium Thread Safety With ThreadGuard
Environments
- Environment:Facebookresearch Habitat lab SLURM Distributed Environment
- Environment:Sgl project Sglang Kubernetes
- Environment:Vllm project Vllm AMD ROCm
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:Fastai Fastbook NLP SpaCy Environment
- Environment:ClickHouse ClickHouse OpenSSL Runtime
- Environment:Huggingface Alignment handbook Evaluation Tools
- Environment:Turboderp org Exllamav2 Build Toolchain
- Environment:Astronomer Astronomer cosmos Cloud Provider Dependencies
- Environment:Cohere ai Cohere python Cohere API Credentials