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:Alibaba MNN LLM Deployment Pipeline
- Workflow:Webdriverio Webdriverio Cloud Service Integration
- Workflow:Elevenlabs Elevenlabs python Speech to Text Transcription
- Workflow:Openai CLIP Prompt engineered classification
- Workflow:Huggingface Datatrove Dataset Tokenization
- Workflow:Vibrantlabsai Ragas Prompt Optimization
- Workflow:Lm sys FastChat LoRA QLoRA Finetuning
- Workflow:Mlc ai Mlc llm Model Compilation
- Workflow:Apache Hudi Flink Table Clustering
- Workflow:Sdv dev SDV Sequential data synthesis
Principles
- Principle:FlagOpen FlagEmbedding Distributed Embedder Training
- Principle:Huggingface Optimum GPTQ Model Conversion
- Principle:Ucbepic Docetl Pipeline Optimization Search
- Principle:TA Lib Ta lib python Abstract Function Instantiation
- Principle:Bigscience workshop Petals Model Evaluation
- Principle:BerriAI Litellm Integration Data Export
- Principle:Mit han lab Llm awq Calibration Data Preparation
- Principle:Webdriverio Webdriverio Command Wrapping
- Principle:Volcengine Verl Multi Turn Rollout
- Principle:Apache Hudi Feature Exploration
Implementations
- Implementation:Kornia Kornia Charbonnier Loss
- Implementation:Fastai Fastbook Text Classifier Learner
- Implementation:Anthropics Anthropic sdk python BetaWebSearchTool 20250305
- Implementation:ArroyoSystems Arroyo Connection Tester
- Implementation:DataExpert io Data engineer handbook Statsig Initialize
- Implementation:Neuml Txtai HFTrainer Call
- Implementation:OpenHands OpenHands SaasNestedConversationManager Refresh Tokens
- Implementation:Haosulab ManiSkill WidowXAI
- Implementation:Microsoft Autogen Studio Generate Image Tool
- Implementation:Neuml Txtai Pipeline Constructors
Heuristics
- Heuristic:Langgenius Dify Celery Queue Separation
- Heuristic:Pyro ppl Pyro Guide Initialization Strategy
- Heuristic:Sail sg LongSpec NCCL Distributed Settings
- Heuristic:Dotnet Machinelearning Text File Sampling Strategy
- Heuristic:Googleapis Python genai AFC Max Remote Calls Limit
- Heuristic:Snorkel team Snorkel NLP Preprocessor Memoization
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
- Heuristic:Iterative Dvc Shell Execution Pitfalls
- Heuristic:Neuml Txtai Batch Size And Sorting Tip
- Heuristic:Arize ai Phoenix Environment Variable Precedence
Environments
- Environment:Datajuicer Data juicer Ray Cluster Environment
- Environment:Alibaba MNN Python Export Environment
- Environment:Nightwatchjs Nightwatch BrowserStack Cloud
- Environment:Alibaba ROLL Megatron Training Environment
- Environment:Dagster io Dagster Container Resource Monitoring
- Environment:Volcengine Verl CUDA GPU Environment
- Environment:Apache Airflow Development Contributor Environment
- Environment:Fede1024 Rust rdkafka CI Test Runner
- Environment:Axolotl ai cloud Axolotl CUDA GPU
- Environment:Allenai Open instruct vLLM Inference