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:Romsto Speculative Decoding Interactive CLI Comparison
- Workflow:Protectai Llm guard LLM Input Output Scanning
- Workflow:Run llama Llama index RAG Query Pipeline
- Workflow:Online ml River Time Series Forecasting
- Workflow:Norrrrrrr lyn WAInjectBench Image Prompt Injection Detection
- Workflow:Unstructured IO Unstructured Connector Ingest Pipeline
- Workflow:AnswerDotAI RAGatouille ColBERT Training
- Workflow:Mistralai Client python OCR Document Processing
- Workflow:EvolvingLMMs Lab Lmms eval Server Mode Evaluation
- Workflow:Helicone Helicone Local Development Setup
Principles
- Principle:Hiyouga LLaMA Factory Dataset Format Conversion
- Principle:Apache Paimon Catalog Object Model
- Principle:Cohere ai Cohere python Finetuning Configuration
- Principle:Haifengl Smile Matrix Arithmetic
- Principle:Dotnet Machinelearning LambdaMART Ranking
- Principle:Infiniflow Ragflow Dataflow Pipeline
- Principle:Getgauge Taiko Gauge Step Implementation
- Principle:Snorkel team Snorkel Task Operation Definition
- Principle:Haifengl Smile SQL Database Connection
- Principle:Apache Druid SQL Schema Configuration
Implementations
- Implementation:Duckdb Duckdb Mbedtls PK
- Implementation:Promptfoo Promptfoo loadApiProvider
- Implementation:Ggml org Llama cpp Memory Header
- Implementation:Deepspeedai DeepSpeed Sparse Attention Utils
- Implementation:Microsoft Onnxruntime CUDA GatherNDGrad
- Implementation:ClickHouse ClickHouse Poco SocketAddress Impl
- Implementation:Online ml River Ensemble VotingClassifier
- Implementation:Triton inference server Server L0 Sagemaker Test
- Implementation:Microsoft Onnxruntime ESLintConfig
- Implementation:NVIDIA NeMo Curator RayDataExecutor
Heuristics
- Heuristic:MaterializeInc Materialize CI Retry Strategies
- Heuristic:Openai Openai node Retry Backoff Configuration
- Heuristic:PeterL1n BackgroundMattingV2 Training Batch Size And Resolution
- Heuristic:Kserve Kserve VLLM GPU Memory Utilization
- Heuristic:Sgl project Sglang Chunked Prefill OOM Prevention
- Heuristic:Online ml River Hoeffding Tree Grace Period Tuning
- Heuristic:Princeton nlp Tree of thought llm Global State Token Counting
- Heuristic:Testtimescaling Testtimescaling github io Dual JSON Sync
- Heuristic:Intel Ipex llm QLoRA Training Hyperparameters
- Heuristic:ARISE Initiative Robomimic Data Worker Tuning By Modality
Environments
- Environment:Dotnet Machinelearning Platform Architecture Support
- Environment:Huggingface Transformers Python 310 Runtime
- Environment:Openai Openai agents python Voice Dependencies
- Environment:Microsoft DeepSpeedExamples VisualChat Training Environment
- Environment:Mlfoundations Open flamingo PyTorch CUDA Distributed
- Environment:PacktPublishing LLM Engineers Handbook VLLM Evaluation Environment
- Environment:Microsoft Onnxruntime Distributed Training Environment
- Environment:Lakeraai Pint benchmark Python 310 With Transformers
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:PacktPublishing LLM Engineers Handbook API Credentials