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:DataExpert io Data engineer handbook Flink Kafka Streaming Pipeline
- Workflow:Risingwavelabs Risingwave Streaming ETL Pipeline
- Workflow:Openai Openai python Chat Completion
- Workflow:ARISE Initiative Robosuite Teleoperation
- Workflow:Anthropics Anthropic sdk python Basic Message Conversation
- Workflow:Vibrantlabsai Ragas Testset Generation
- Workflow:Openai Evals Creating a model graded eval
- Workflow:Bitsandbytes foundation Bitsandbytes 4bit QLoRA Inference
- Workflow:FlagOpen FlagEmbedding Benchmark Evaluation
- Workflow:Cleanlab Cleanlab Multiannotator Consensus
Principles
- Principle:Interpretml Interpret Interactive Visualization Rendering
- Principle:LaurentMazare Tch rs Seq2Seq Dataset Loading
- Principle:Mage ai Mage ai Singer Message Emission
- Principle:Alibaba MNN LLM Inference Execution
- Principle:Princeton nlp Tree of thought llm Thought Evaluation
- Principle:Apache Flink Async Sink Configuration
- Principle:Eventual Inc Daft Window Functions
- Principle:ClickHouse ClickHouse Type Safe Wrappers
- Principle:Avhz RustQuant Exotic Option Contracts
- Principle:Roboflow Rf detr COCO Evaluation
Implementations
- Implementation:Protectai Llm guard Input BanCompetitors
- Implementation:Evidentlyai Evidently Legacy Text Evals Preset
- Implementation:Openai Evals Get Jsonl
- Implementation:InternLM Lmdeploy RequestLogger
- Implementation:Mlc ai Mlc llm Param Mapping
- Implementation:Apache Paimon IndexManifestFile
- Implementation:Google deepmind Mujoco XML Util
- Implementation:Sail sg LongSpec APPS Code Evaluator
- Implementation:Pola rs Polars SQL Collect and Output
- Implementation:Openai Openai python Realtime Conversation Item Create
Heuristics
- Heuristic:Alibaba MNN Weight Quantization Strategy
- Heuristic:Deepspeedai DeepSpeed FP16 Convergence Tips
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Tensorflow Serving Model Warmup Strategy
- Heuristic:Openai Openai python Warning Deprecated Eval Stored Completions
- Heuristic:Iamhankai Forest of Thought Self Correction Confidence Threshold
- Heuristic:AUTOMATIC1111 Stable diffusion webui GTX 16 Series FP16 Workaround
- Heuristic:Openclaw Openclaw Cache TTL Asymmetric Strategy
- Heuristic:Nautechsystems Nautilus trader Streaming Mode For Large Backtests
Environments
- Environment:LaurentMazare Tch rs Python Interop Environment
- Environment:Kserve Kserve Kubernetes Cluster
- Environment:Unslothai Unsloth Llama Cpp
- Environment:Guardrails ai Guardrails Python 3 10 Runtime
- Environment:Ray project Ray Docker GPU Environment
- Environment:Volcengine Verl Megatron Core Environment
- Environment:Openai Evals Python Runtime
- Environment:ARISE Initiative Robomimic Robosuite Simulation Backend
- Environment:Scikit learn Scikit learn OpenMP Thread Configuration
- Environment:Puppeteer Puppeteer Cross Platform Browser Environment