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:Lm sys FastChat MT Bench Evaluation
- Workflow:Scikit learn Scikit learn Cross Validation Evaluation
- Workflow:Groq Groq python Chat Completion
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
- Workflow:Pola rs Polars Data IO and Format Conversion
- Workflow:Dotnet Machinelearning GenAI Causal LM Inference
- Workflow:Liu00222 Open Prompt Injection Detection Localization Defense
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:Ollama Ollama OpenAI API Compatibility
- Workflow:OpenRLHF OpenRLHF Rejection Sampling
Principles
- Principle:OpenRLHF OpenRLHF Agent Based Rollout Collection
- Principle:Kornia Kornia Gradient Edge Detection
- Principle:Norrrrrrr lyn WAInjectBench Detection Rate Computation
- Principle:Huggingface Transformers Benchmark Orchestration V1
- Principle:Huggingface Datasets Parquet Dataset Building
- Principle:PacktPublishing LLM Engineers Handbook Vector Similarity Search
- Principle:Liu00222 Open Prompt Injection Task Creation
- Principle:OWASP Www project top 10 for large language model applications Translation Quality Review
- Principle:Ray project Ray Runtime Shutdown
- Principle:NVIDIA NeMo Aligner Critic Server Deployment
Implementations
- Implementation:DataExpert io Data engineer handbook Pytest Spark Fixture
- Implementation:Alibaba ROLL ModelUtils
- Implementation:Turboderp org Exllamav2 ExLlamaV2DynamicGeneratorAsync
- Implementation:CARLA simulator Carla Navigation
- Implementation:Langchain ai Langgraph Pregel Invoke For Agents
- Implementation:DistrictDataLabs Yellowbrick DecisionBoundariesVisualizer
- Implementation:Langgenius Dify Completion Params
- Implementation:Microsoft Onnxruntime NNAPIFlags
- Implementation:Huggingface Optimum Get Dataset
- Implementation:Helicone Helicone SSO Page
Heuristics
- Heuristic:Haotian liu LLaVA Tokenizer Version Offset Correction
- Heuristic:Nautechsystems Nautilus trader Parquet Row Group Tuning
- Heuristic:Vespa engine Vespa Warning Deprecated Cloud API Constructors
- Heuristic:Apache Kafka Coordinator Loading Commit Interval
- Heuristic:Fastai Fastbook Mixup Data Augmentation
- Heuristic:Mlflow Mlflow Batch Logging Size Limits
- Heuristic:Guardrails ai Guardrails Async Vs Sync Validation Mode
- Heuristic:VainF Torch Pruning AutoGrad Dependency Graph
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:Pytorch Serve Ampere Tensor Core Optimization
Environments
- Environment:DevExpress Testcafe Node Runtime
- Environment:Pyro ppl Pyro Python PyTorch Core
- Environment:Astronomer Astronomer cosmos Cosmos Airflow Configuration
- Environment:NVIDIA DALI CUDA GPU Environment
- Environment:Huggingface Diffusers PyTorch CUDA Runtime
- Environment:Kserve Kserve VLLM Runtime
- Environment:Alibaba ROLL Megatron Training Environment
- Environment:Huggingface Datatrove S3 Storage Environment
- Environment:Datahub project Datahub Docker Quickstart Environment
- Environment:Huggingface Datasets Search Dependencies