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:Langchain ai Langgraph Functional API Workflow
- Workflow:Dagster io Dagster ETL Pipeline
- Workflow:Duckdb Duckdb Building From Source
- Workflow:Gretelai Gretel synthetics LSTM Text Generation
- Workflow:MaterializeInc Materialize Release Process
- Workflow:Openai Evals Building a custom eval
- Workflow:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:SeldonIO Seldon core Model Explainability
- Workflow:Huggingface Diffusers DreamBooth Personalization
- Workflow:SeldonIO Seldon core Inference Pipeline
Principles
- Principle:Langgenius Dify SSRFPrevention
- Principle:Trailofbits Fickling Import Level Pickle Interception
- Principle:DistrictDataLabs Yellowbrick Silhouette Analysis
- Principle:Run llama Llama index Evaluation Result Analysis
- Principle:Kubeflow Kubeflow Component Deployment
- Principle:Isaac sim IsaacGymEnvs Task Selection and Configuration
- Principle:AUTOMATIC1111 Stable diffusion webui Face restoration
- Principle:Haifengl Smile SQL Database Connection
- Principle:Ggml org Llama cpp CLI Argument Parsing
- Principle:Apache Dolphinscheduler Plugin Artifact Provisioning
Implementations
- Implementation:Arize ai Phoenix Legacy LiteLLMModel
- Implementation:Duckdb Duckdb Release Upload Scripts
- Implementation:DevExpress Testcafe Selector API
- Implementation:NVIDIA DALI EfficientDet HParams
- Implementation:Google deepmind Dm control Build Dog
- Implementation:Openai Openai python Image Edit Completed Event
- Implementation:Datahub project Datahub Pip Install Acryl Datahub
- Implementation:Fede1024 Rust rdkafka StreamConsumer Stream
- Implementation:Unstructured IO Unstructured PartitionStrategy
- Implementation:Openai Openai agents python Non Strict Output Type Pattern
Heuristics
- Heuristic:Alibaba MNN LLM Runtime Tuning
- Heuristic:CrewAIInc CrewAI LLM Provider Message Workarounds
- Heuristic:Hiyouga LLaMA Factory LoRA DDP Configuration
- Heuristic:Fede1024 Rust rdkafka Librdkafka Debug Logging
- Heuristic:Kornia Kornia Numerical Stability Patterns
- Heuristic:Treeverse LakeFS Action Cache Wait Tip
- Heuristic:NVIDIA TransformerEngine Build Optimization Tips
- Heuristic:Deepspeedai DeepSpeed FP16 Convergence Tips
- Heuristic:Bigscience workshop Petals Randomized Rebalancing Intervals
- Heuristic:Microsoft LoRA Label Smoothing NLG
Environments
- Environment:Danijar Dreamerv3 JAX CUDA
- Environment:Farama Foundation Gymnasium Video Recording Dependencies
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:Truera Trulens Streamlit Dashboard Environment
- Environment:Huggingface Alignment handbook Python TRL
- Environment:CARLA simulator Carla Simulation Runtime
- Environment:Elevenlabs Elevenlabs python FFmpeg Mpv
- Environment:Huggingface Transformers PyTorch 24 CUDA
- Environment:OpenBMB UltraFeedback vLLM Multi GPU Environment
- Environment:Bentoml BentoML BentoCloud Credentials