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:Lakeraai Pint benchmark Custom System Evaluation
- Workflow:Mlflow Mlflow Prompt Management
- Workflow:Axolotl ai cloud Axolotl Multimodal Vision Finetuning
- Workflow:Run llama Llama index Embedding Finetuning
- Workflow:Alibaba ROLL Reward Flow Diffusion Pipeline
- Workflow:Googleapis Python genai Function Calling and Tools
- Workflow:Facebookresearch Habitat lab Agent Benchmarking
- Workflow:Scikit learn Scikit learn Supervised Classification
- Workflow:Langgenius Dify Workflow Builder and Execution
- Workflow:Mlc ai Web llm Function Calling
Principles
- Principle:AUTOMATIC1111 Stable diffusion webui Model Identification
- Principle:Huggingface Alignment handbook LLM Evaluation Benchmarks
- Principle:Rapidsai Cuml Clustering Evaluation
- Principle:ClickHouse ClickHouse Submodule Initialization
- Principle:MaterializeInc Materialize Multi Backend Data Ingestion
- Principle:DataTalksClub Data engineering zoomcamp Dbt Staging Layer
- Principle:Unslothai Unsloth Vision LoRA Injection
- Principle:Infiniflow Ragflow Application Embedding
- Principle:Vespa engine Vespa Indexing Expression Execution
- Principle:Astronomer Astronomer cosmos Kubernetes Operator Execution
Implementations
- Implementation:Evidentlyai Evidently Legacy Sentiment Feature
- Implementation:Princeton nlp Tree of thought llm Test Output
- Implementation:Tencent Ncnn YOLOv8 Seg Example
- Implementation:Tensorflow Serving Tfrt Saved Model With Batching Test
- Implementation:MaterializeInc Materialize MaterializeAdapter Relations
- Implementation:SeldonIO Seldon core Seldon Pipeline Infer
- Implementation:Run llama Llama index PII Postprocessors
- Implementation:FMInference FlexLLMGen Compute Metrics
- Implementation:Sdv dev SDV Download Demo
- Implementation:BerriAI Litellm Litellm Logging
Heuristics
- Heuristic:Deepseek ai Janus Bfloat16 Dtype Selection
- Heuristic:Microsoft DeepSpeedExamples RLHF Stability Constraints
- Heuristic:ThreeSR Awesome Inference Time Scaling Date Parsing Fallback Tip
- Heuristic:Bigscience workshop Petals Prompt Embeddings Float32 Precision
- Heuristic:Getgauge Taiko Browser Launch Flags
- Heuristic:Obss Sahi Overlap Ratio Selection
- Heuristic:MarketSquare Robotframework browser GRPC Response Chunking
- Heuristic:Princeton nlp Tree of thought llm Value Caching
- Heuristic:Datahub project Datahub Gradle Task Only
- Heuristic:Cohere ai Cohere python ToolCallV2 Auto UUID Override
Environments
- Environment:Cypress io Cypress Browser Requirements
- Environment:Deepseek ai Janus JanusFlow Diffusers Environment
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Guardrails ai Guardrails Docker Server Runtime
- Environment:Mlflow Mlflow OpenAI LLM Integration Environment
- Environment:Promptfoo Promptfoo Provider API Keys
- Environment:Deepset ai Haystack OpenAI API Environment
- Environment:Bigscience workshop Petals CUDA Server
- Environment:Mlc ai Mlc llm TVM Runtime Environment
- Environment:Helicone Helicone Node 20 TypeScript Runtime