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 Semantic kernel Process Orchestration
- Workflow:Deepspeedai DeepSpeed Pipeline Parallel Training
- Workflow:Elevenlabs Elevenlabs python Speech to Text Transcription
- Workflow:Wandb Weave Prompt Management
- Workflow:Unslothai Unsloth Model Export And Deployment
- Workflow:Interpretml Interpret Blackbox Model Explanation
- Workflow:Lakeraai Pint benchmark Hugging Face Model Evaluation
- Workflow:Promptfoo Promptfoo Project Initialization
- Workflow:OWASP Www project top 10 for large language model applications GenAI Red Team Testing
- Workflow:SeldonIO Seldon core Inference Pipeline
Principles
- Principle:Microsoft Agent framework Executor Definition
- Principle:Online ml River Holt Winters Forecasting
- Principle:Eric mitchell Direct preference optimization Dropout Disabling
- Principle:CARLA simulator Carla A Star Route Planning
- Principle:CARLA simulator Carla Traffic Behavior Configuration
- Principle:Google deepmind Mujoco Model Initialization
- Principle:Explodinggradients Ragas DSPy Prompt Optimization
- Principle:Isaac sim IsaacGymEnvs Environment Setup
- Principle:Zai org CogVideo MoVQ Decoder Architecture
- Principle:Mbzuai oryx Awesome LLM Post training Publication Count Querying
Implementations
- Implementation:Iterative Dvc Api Experiments
- Implementation:FMInference FlexLLMGen CompressionConfig
- Implementation:Mlc ai Mlc llm MoE Matmul
- Implementation:Pyro ppl Pyro HorovodOptimizer
- Implementation:NVIDIA NeMo Aligner Prepare Packed DPO Dataset
- Implementation:BerriAI Litellm CLI Token Utils
- Implementation:FlagOpen FlagEmbedding LLARA Finetune Data
- Implementation:Open compass VLMEvalKit SArena DINO Score
- Implementation:Evidentlyai Evidently SDK Adapters
- Implementation:Mlflow Mlflow Set Model Version Tag
Heuristics
- Heuristic:PrefectHQ Prefect SQLite Performance Tuning
- Heuristic:Promptfoo Promptfoo Adaptive Concurrency Tuning
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:Trailofbits Fickling Injection Mode Selection
- Heuristic:Iamhankai Forest of Thought Tree Iteration Scaling
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Princeton nlp SimPO Concatenated Forward Pass
- Heuristic:PrefectHQ Prefect Retry Backoff Strategy
- Heuristic:Wandb Weave Retry And Error Handling
- Heuristic:Puppeteer Puppeteer Chrome Default Launch Arguments
Environments
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:OpenRLHF OpenRLHF Ray Distributed Environment
- Environment:Heibaiying BigData Notes Kafka 2 2 Environment
- Environment:Shiyu coder Kronos HuggingFace Hub Access
- Environment:Huggingface Datatrove S3 Storage Environment
- Environment:Openai Openai node Node 20 Runtime
- Environment:Togethercomputer Together python Python SDK Runtime
- Environment:Cypress io Cypress Linux Display Server
- Environment:DataTalksClub Data engineering zoomcamp Dlt BigQuery Environment
- Environment:Elevenlabs Elevenlabs python FFmpeg Mpv