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:Cohere ai Cohere python Semantic Search With Rerank
- Workflow:Vibrantlabsai Ragas RAG Evaluation
- Workflow:LaurentMazare Tch rs LLM Text Generation
- Workflow:Microsoft Autogen Graph Based Agent Orchestration
- Workflow:Microsoft Agent framework Declarative Agent Definition
- Workflow:Alibaba ROLL Agentic RL Training Pipeline
- Workflow:Allenai Open instruct Tulu3 Full Post Training
- Workflow:Apache Airflow Scheduler Operation and Task Execution
- Workflow:Axolotl ai cloud Axolotl Full Finetuning Distributed
- Workflow:Tencent Ncnn Image Classification Inference
Principles
- Principle:Huggingface Diffusers Training Dataset Preparation
- Principle:Onnx Onnx External Data Conversion
- Principle:Anthropics Anthropic sdk python Tool Call Detection
- Principle:AUTOMATIC1111 Stable diffusion webui Diagnostics
- Principle:Eventual Inc Daft Error Hierarchy
- Principle:Tensorflow Serving Container Registry Push
- Principle:Rapidsai Cuml Clustering Algorithm Configuration
- Principle:Haotian liu LLaVA LoRA Training
- Principle:Anthropics Anthropic sdk python Output Schema Definition
- Principle:InternLM Lmdeploy SmoothQuant Quantization
Implementations
- Implementation:Protectai Llm guard Input Scanner Base
- Implementation:Open compass VLMEvalKit VinternChat
- Implementation:Neuml Txtai Sparse Scoring
- Implementation:OpenGVLab InternVL Evaluate Sh
- Implementation:Apache Paimon RESTCatalogOptions
- Implementation:Apache Paimon ConfigOption
- Implementation:EvolvingLMMs Lab Lmms eval VideoMathQA CoT Step Evaluation
- Implementation:Facebookresearch Audiocraft RotaryEmbedding
- Implementation:SeldonIO Seldon core Seldon Pipeline CRD Multi Modal
- Implementation:DistrictDataLabs Yellowbrick GridSearchColorPlot
Heuristics
- Heuristic:Spotify Luigi Marker Table Idempotency
- Heuristic:Scikit learn contrib Imbalanced learn Sparse Matrix Handling
- Heuristic:FMInference FlexLLMGen Pin Memory Tradeoffs
- Heuristic:Mlc ai Mlc llm GPU Memory Budget Tuning
- Heuristic:Mlc ai Web llm Multi Round KV Cache Reuse
- Heuristic:Microsoft Agent framework Async Context Manager Cleanup
- Heuristic:Astronomer Astronomer cosmos Dbt Invocation Mode Selection
- Heuristic:Langchain ai Langchain Warning Deprecated Langchain Classic
- Heuristic:DevExpress Testcafe Assertion Retry Timing
- Heuristic:PeterL1n BackgroundMattingV2 Backbone Scale Selection
Environments
- Environment:Speechbrain Speechbrain Multi GPU DDP
- Environment:Shiyu coder Kronos DDP Multi GPU Environment
- Environment:Farama Foundation Gymnasium Box2D Physics Backend
- Environment:Datahub project Datahub Frontend Build
- Environment:SeldonIO Seldon core Python ML Dependencies Environment
- Environment:Protectai Llm guard Python Runtime Dependencies
- Environment:Volcengine Verl Megatron Core Environment
- Environment:Lakeraai Pint benchmark Python 310 With Pandas
- Environment:Truera Trulens Snowflake Connector Environment
- Environment:Intel Ipex llm NPU Cpp Environment