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:Scikit learn contrib Imbalanced learn Ensemble Imbalanced Classification
- Workflow:Google research Deduplicate text datasets Suffix array querying
- Workflow:Farama Foundation Gymnasium Custom Environment Creation
- Workflow:ClickHouse ClickHouse Running Stateless Tests
- Workflow:Anthropics Anthropic sdk python Streaming Message Interaction
- Workflow:Kserve Kserve Canary Rollout Deployment
- Workflow:Deepseek ai Janus Multimodal Understanding
- Workflow:Haosulab ManiSkill Imitation Learning Pipeline
- Workflow:FMInference FlexLLMGen Data Wrangling Batch Inference
- Workflow:Roboflow Rf detr Object Detection Inference
Principles
- Principle:Axolotl ai cloud Axolotl DPO Training Execution
- Principle:Scikit learn contrib Imbalanced learn Combined Over Under Sampling
- Principle:Zai org CogVideo Scheduler Configuration
- Principle:Microsoft Autogen Model Client Configuration
- Principle:AUTOMATIC1111 Stable diffusion webui Network file discovery
- Principle:NVIDIA NeMo Curator Video Frame Extraction
- Principle:Deepseek ai Janus JanusFlow Model Loading
- Principle:MaterializeInc Materialize Docker Image Building
- Principle:Nightwatchjs Nightwatch Client Initialization
- Principle:ArroyoSystems Arroyo Connection Testing
Implementations
- Implementation:Ollama Ollama Imagegen Transfer
- Implementation:Avhz RustQuant HullWhite Process
- Implementation:Ggml org Llama cpp Unicode Header
- Implementation:AUTOMATIC1111 Stable diffusion webui StableDiffusionProcessingTxt2Img
- Implementation:FlowiseAI Flowise VariablesView
- Implementation:Apache Spark UI Test NPM Lock
- Implementation:Open compass VLMEvalKit WeMath Utils
- Implementation:Unslothai Unsloth MoE Ops
- Implementation:Recommenders team Recommenders Benchmark Predict And Recommend
- Implementation:Explodinggradients Ragas DataCompyScore Metric
Heuristics
- Heuristic:ArroyoSystems Arroyo Worker Heartbeat Timeout
- Heuristic:Datahub project Datahub Venv Copies Mode
- Heuristic:Neuml Txtai Memory Streaming Optimization
- Heuristic:DevExpress Testcafe Docker Chrome Tab Retry
- Heuristic:LLMBook zh LLMBook zh github io IGNORE INDEX Loss Masking
- Heuristic:Pytorch Serve Batch Size Tuning
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:DevExpress Testcafe Video Encoding Defaults
- Heuristic:CarperAI Trlx KL Coefficient Adaptation
- Heuristic:Vllm project Vllm Attention Backend Selection
Environments
- Environment:Elevenlabs Elevenlabs python Python Httpx
- Environment:MaterializeInc Materialize Dbt Materialize Runtime
- Environment:Kubeflow Kubeflow Python KFP SDK Environment
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:PacktPublishing LLM Engineers Handbook VLLM Evaluation Environment
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Volcengine Verl Ray Distributed Environment
- Environment:Google research Deduplicate text datasets Python HuggingFace Environment
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:Heibaiying BigData Notes Hadoop CDH Environment