Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Huggingface Optimum Accelerated Inference Pipeline
- Workflow:Openai Openai python Audio Processing
- Workflow:Google deepmind Mujoco GPU batched simulation MJX
- Workflow:Infiniflow Ragflow Document Processing Pipeline
- Workflow:Wandb Weave Prompt Management
- Workflow:Explodinggradients Ragas Agent Evaluation
- Workflow:Scikit learn contrib Imbalanced learn SMOTE Resampling Pipeline
- Workflow:Hiyouga LLaMA Factory PPO RLHF Training
- Workflow:Treeverse LakeFS Write Audit Publish With Hooks
- Workflow:Mlfoundations Open flamingo Data Preparation
Principles
- Principle:Openai Openai agents python Output Processing
- Principle:Getgauge Taiko Checkbox Interaction
- Principle:OWASP Www project top 10 for large language model applications Assessment Report Generation
- Principle:Apache Paimon Atomic Commit
- Principle:Isaac sim IsaacGymEnvs Runtime Randomization
- Principle:Triton inference server Server Ensemble Validation
- Principle:Norrrrrrr lyn WAInjectBench Environment Setup
- Principle:Infiniflow Ragflow Graph State Management
- Principle:TobikoData Sqlmesh Incremental Model Definition
- Principle:Deepspeedai DeepSpeed DeepSpeed Configuration
Implementations
- Implementation:LMCache LMCache LMCacheConnectorV1Impl Init
- Implementation:Langchain ai Langgraph BaseChannel
- Implementation:Deepspeedai DeepSpeed SHM Allreduce
- Implementation:LMCache LMCache Bypass Lookup Client
- Implementation:Langchain ai Langgraph StoreEmbedding
- Implementation:Apache Flink SplitFetcher
- Implementation:Protectai Llm guard Output Toxicity
- Implementation:Unslothai Unsloth Save Pretrained GGUF
- Implementation:Haosulab ManiSkill MP Solutions Pattern
- Implementation:ARISE Initiative Robosuite SimpleGripController
Heuristics
- Heuristic:Nightwatchjs Nightwatch Warning Deprecated API Members
- Heuristic:Openai Openai node Retry Backoff Configuration
- Heuristic:BerriAI Litellm Retry Backoff Strategy
- Heuristic:Huggingface Alignment handbook EOS Token Alignment
- Heuristic:Openai Whisper Log Probability Threshold
- Heuristic:Mistralai Client python Retry Backoff Strategy
- Heuristic:Gretelai Gretel synthetics GPU Memory Allow Growth
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Datajuicer Data juicer Batch Size Adaptation
Environments
- Environment:Mlc ai Web llm WebGPU Browser Runtime
- Environment:OWASP Www project top 10 for large language model applications PR Description Generator Runtime
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies
- Environment:Open compass VLMEvalKit Data Storage Environment
- Environment:SeldonIO Seldon core Kubernetes Cluster Environment
- Environment:Mlfoundations Open flamingo WebDataset Training Dependencies
- Environment:ContextualAI HALOs CUDA 12 1 Training Environment
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Farama Foundation Gymnasium Python 3 10 Runtime
- Environment:PrefectHQ Prefect Python Runtime Environment