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:Microsoft LoRA LoRA Integration
- Workflow:Huggingface Transformers PEFT Adapter Integration
- Workflow:OpenGVLab InternVL Supervised Finetuning
- Workflow:Mlc ai Web llm Chrome Extension Integration
- Workflow:AUTOMATIC1111 Stable diffusion webui Image postprocessing and upscaling
- Workflow:Haosulab ManiSkill Motion Planning Demo Generation
- Workflow:Datahub project Datahub Protobuf Schema Ingestion
- Workflow:Bigscience workshop Petals Server Contribution
- Workflow:NVIDIA DALI Image Classification Training PyTorch
- Workflow:Intel Ipex llm QLoRA Finetuning
Principles
- Principle:Googleapis Python genai Live Streaming
- Principle:Unstructured IO Unstructured Basic Chunking
- Principle:Astronomer Astronomer cosmos Dataset Lineage
- Principle:Openai Whisper Mel Spectrogram Computation
- Principle:Microsoft Agent framework Chat Client Configuration
- Principle:Intel Ipex llm DPO Data Preparation
- Principle:Langchain ai Langchain Tool Binding
- Principle:Neuml Txtai Index Persistence
- Principle:Heibaiying BigData Notes Kafka Producer Configuration
- Principle:Treeverse LakeFS Commit
Implementations
- Implementation:LaurentMazare Tch rs Torch Jit Trace
- Implementation:InternLM Lmdeploy Autotest Config
- Implementation:Iterative Dvc VegaConverter Convert
- Implementation:FlagOpen FlagEmbedding LLM Reranker Instruction Data
- Implementation:Online ml River Cluster ODAC
- Implementation:OWASP Www project top 10 for large language model applications Markdown To PDF Convert
- Implementation:Langfuse Langfuse EvalRouter CreateTemplate
- Implementation:Huggingface Datatrove JapaneseTokenizer
- Implementation:Hpcaitech ColossalAI GSMDataset
- Implementation:CrewAIInc CrewAI Docs Navigation Config
Heuristics
- Heuristic:Vespa engine Vespa KStemmer Dictionary Loading
- Heuristic:Iterative Dvc Shell Execution Pitfalls
- Heuristic:Apache Spark K8s Container Patterns
- Heuristic:CrewAIInc CrewAI RAG Search Defaults
- Heuristic:FlagOpen FlagEmbedding Same Dataset Batching Tip
- Heuristic:Astronomer Astronomer cosmos Static Parser Hang Workaround
- Heuristic:CarperAI Trlx Delta Rewards
- Heuristic:Speechbrain Speechbrain Score Normalization Tips
- Heuristic:AUTOMATIC1111 Stable diffusion webui NaN Detection And Precision Fixes
- Heuristic:Kubeflow Kubeflow Issue Routing To Sub Repos
Environments
- Environment:Deepseek ai Janus JanusFlow Diffusers Environment
- Environment:Intel Ipex llm NPU Environment
- Environment:ArroyoSystems Arroyo Webui Runtime
- Environment:Explodinggradients Ragas LLM Provider Environment
- Environment:Huggingface Alignment handbook DeepSpeed Multi Node
- Environment:Zai org CogVideo Video Captioning Environment
- Environment:SeleniumHQ Selenium Selenium Manager Runtime
- Environment:Cleanlab Cleanlab Python Core Environment
- Environment:PacktPublishing LLM Engineers Handbook Selenium Chrome Crawler Environment
- Environment:Googleapis Python genai Python 3 10 SDK Runtime