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:Predibase Lorax Multi Adapter Merging
- Workflow:AUTOMATIC1111 Stable diffusion webui Image to image generation
- Workflow:Openai Openai python Responses API Text Generation
- Workflow:Arize ai Phoenix Trace Ingestion Pipeline
- Workflow:Fede1024 Rust rdkafka At Least Once Processing
- Workflow:Intel Ipex llm Pipeline Parallel Inference
- Workflow:Mit han lab Llm awq TinyChat LLM Deployment
- Workflow:Huggingface Optimum Model Export
- Workflow:Trailofbits Fickling Pickle Decompilation and Tracing
- Workflow:Tensorflow Tfjs Transfer Learning
Principles
- Principle:Openai Whisper Punctuation Merging
- Principle:Pola rs Polars Time Series Resampling
- Principle:Microsoft Semantic kernel Process Execution
- Principle:Microsoft Autogen Graph Flow Configuration
- Principle:Zai org CogVideo UNet Backbone
- Principle:Explodinggradients Ragas Metric Baseline Correlation
- Principle:Huggingface Transformers Distributed Process Initialization
- Principle:Vespa engine Vespa Text Transformation
- Principle:Kubeflow Pipelines Conditional Branching
- Principle:Princeton nlp Tree of thought llm DFS Tree Search
Implementations
- Implementation:Bentoml BentoML DefaultMonitor
- Implementation:Datajuicer Data juicer TextEntityDependencyFilter
- Implementation:Danijar Dreamerv3 Make Replay
- Implementation:Mlc ai Mlc llm Engine Action
- Implementation:Vllm project Vllm StructuredOutputsParams Init
- Implementation:Vibrantlabsai Ragas HuggingFaceEmbeddings
- Implementation:Mlc ai Web llm Function Calling Model Ids
- Implementation:Datajuicer Data juicer VideoSplitByDurationMapper
- Implementation:Evidentlyai Evidently Legacy Text Contains Feature
- Implementation:Facebookresearch Audiocraft MusicDataset init
Heuristics
- Heuristic:Vllm project Vllm Attention Backend Selection
- Heuristic:Openai CLIP CLIP Normalization Constants
- Heuristic:FlowiseAI Flowise Edge Connection Type Matching
- Heuristic:Datahub project Datahub Warning Deprecated Spark Lineage Legacy
- Heuristic:EvolvingLMMs Lab Lmms eval Truncated Image Handling
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:Haotian liu LLaVA Tokenizer Version Offset Correction
- Heuristic:Turboderp org Exllamav2 Paged Cache Configuration
- Heuristic:Zai org CogVideo Training Hyperparameter Defaults
- Heuristic:Huggingface Open r1 Reward Function Tuning
Environments
- Environment:Cypress io Cypress Linux Display Server
- Environment:Evidentlyai Evidently Python Core Environment
- Environment:Promptfoo Promptfoo SQLite Database
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Huggingface Trl PEFT LoRA Environment
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Scikit learn contrib Imbalanced learn Keras TensorFlow
- Environment:Apache Shardingsphere ZooKeeper Cluster Coordination
- Environment:Datahub project Datahub Java 17 Backend Environment
- Environment:CARLA simulator Carla Python API Runtime