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:Dotnet Machinelearning ONNX Model Scoring
- Workflow:Ggml org Llama cpp Interactive Chat
- Workflow:Guardrails ai Guardrails Server Deployment
- Workflow:Openai CLIP Linear probe evaluation
- Workflow:Groq Groq python Text Embedding
- Workflow:Huggingface Datatrove Common Crawl Processing
- Workflow:Vibrantlabsai Ragas RAG Evaluation
- Workflow:Langchain ai Langgraph CLI Deployment
- Workflow:Haotian liu LLaVA LoRA Finetuning
- Workflow:Dagster io Dagster DSPy Optimization
Principles
- Principle:Webdriverio Webdriverio TestFrameworkIntegration
- Principle:Risingwavelabs Risingwave Streaming Source Ingestion
- Principle:Vllm project Vllm Structured Output Engine Initialization
- Principle:Arize ai Phoenix Prompt Versioning
- Principle:Spcl Graph of thoughts Validity Filtering
- Principle:Axolotl ai cloud Axolotl Package Build Configuration
- Principle:Togethercomputer Together python Fine Tuning Job Monitoring
- Principle:Anthropics Anthropic sdk python Provider Client Initialization
- Principle:Haotian liu LLaVA Environment Setup
- Principle:Bentoml BentoML Async Execution Patterns
Implementations
- Implementation:Langchain ai Langgraph Pregel Invoke For Functional
- Implementation:SeldonIO Seldon core Alibi Detect Training
- Implementation:Datajuicer Data juicer BaseFormatter
- Implementation:Neuml Txtai Microphone
- Implementation:Openclaw Openclaw ResolveSandboxConfigForAgent
- Implementation:Ollama Ollama Llama Mmap
- Implementation:Datajuicer Data juicer WhitespaceNormalizationMapper
- Implementation:Avhz RustQuant OrderType
- Implementation:Apache Beam StreamingEngineComputationConfigFetcher
- Implementation:Datajuicer Data juicer DocumentMinhashDeduplicator
Heuristics
- Heuristic:Apache Dolphinscheduler Failover Marker TTL
- Heuristic:Huggingface Transformers Mixed Precision Training Selection
- Heuristic:Bentoml BentoML Adaptive Batching Tuning
- Heuristic:Openai Evals Event Batching Configuration
- Heuristic:Snorkel team Snorkel Minimum Three LFs
- Heuristic:Elevenlabs Elevenlabs python Text Chunking Splitter Characters
- Heuristic:Cleanlab Cleanlab Object Detection Scoring Constants
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Langfuse Langfuse Ingestion Date Boundary Delay
- Heuristic:Microsoft Semantic kernel Telemetry Log Level Configuration
Environments
- Environment:Allenai Open instruct vLLM Inference
- Environment:Openclaw Openclaw State Directory And Credentials
- Environment:Vllm project Vllm CPU Runtime
- Environment:Evidentlyai Evidently SQL Storage Environment
- Environment:Tencent Ncnn Vulkan Environment
- Environment:Truera Trulens OpenAI Provider Environment
- Environment:Kornia Kornia CUDA GPU Environment
- Environment:Turboderp org Exllamav2 Flash Attention Backend
- Environment:Bigscience workshop Petals CUDA Server
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas