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:Mlfoundations Open flamingo Data Preparation
- Workflow:Huggingface Datatrove Common Crawl Processing
- Workflow:Norrrrrrr lyn WAInjectBench Text Prompt Injection Detection
- Workflow:Predibase Lorax Multi Adapter Merging
- Workflow:OWASP Www project top 10 for large language model applications Agentic Security Assessment
- Workflow:CrewAIInc CrewAI Knowledge RAG Pipeline
- Workflow:FMInference FlexLLMGen Single GPU Offloaded Inference
- Workflow:Vespa engine Vespa Config subscription lifecycle
- Workflow:Run llama Llama index ReAct Agent
- Workflow:Deepset ai Haystack Hybrid Document Search
Principles
- Principle:ClickHouse ClickHouse BFloat16 Type
- Principle:Pyro ppl Pyro Coalescent Process
- Principle:Huggingface Datasets Extension Module Mapping
- Principle:NVIDIA NeMo Curator CLIP Embedding
- Principle:Infiniflow Ragflow Search LLM Settings
- Principle:Open compass VLMEvalKit Judge LLM Construction
- Principle:PrefectHQ Prefect HTML Parsing
- Principle:Openai Openai python Structured Output Definition
- Principle:Rapidsai Cuml Model Explainability
- Principle:CARLA simulator Carla Sensor Attachment
Implementations
- Implementation:Online ml River Datasets Phishing
- Implementation:MarketSquare Robotframework browser Rfbrowser Install
- Implementation:Apache Beam BeamBatchWorker Execute
- Implementation:EvolvingLMMs Lab Lmms eval GEdit Bench Utils
- Implementation:Openai Openai python Pydantic Compat
- Implementation:Intel Ipex llm vLLM Generate
- Implementation:Google deepmind Mujoco MJX Ray
- Implementation:Huggingface Datasets SparkDatasetReader
- Implementation:Lm sys FastChat Gen Judgment
- Implementation:Open compass VLMEvalKit CMMMU
Heuristics
- Heuristic:Apache Airflow Task Dependency Isolation
- Heuristic:Zai org CogVideo Scheduler and Guidance Selection
- Heuristic:Cohere ai Cohere python Tokenizer Cache With TTL
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Mlc ai Mlc llm OpenCL Memory Floor Workaround
- Heuristic:Fede1024 Rust rdkafka Transaction Error Recovery
- Heuristic:Alibaba ROLL Gradient Checkpointing Recomputation
- Heuristic:Zai org CogVideo Training Hyperparameter Defaults
- Heuristic:DevExpress Testcafe CDP Performance Monitoring
- Heuristic:Apache Druid Capability Detection Strategy
Environments
- Environment:Huggingface Trl Quantization Environment
- Environment:Interpretml Interpret Blackbox Explainer Dependencies
- Environment:Microsoft BIPIA OpenAI API Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas
- Environment:Facebookresearch Habitat lab SLURM Distributed Environment
- Environment:Huggingface Alignment handbook Python Transformers
- Environment:Huggingface Trl vLLM Generation Environment
- Environment:MaterializeInc Materialize Dbt Materialize Runtime
- Environment:Huggingface Diffusers Training Environment
- Environment:Apache Spark Kubernetes Runtime