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:Openai Evals Building a custom eval
- Workflow:Microsoft Autogen Graph Based Agent Orchestration
- Workflow:Fastai Fastbook Tabular Modeling
- Workflow:Anthropics Anthropic sdk python Extended Thinking Reasoning
- Workflow:Openai CLIP Linear probe evaluation
- Workflow:Datahub project Datahub Python Metadata Emission
- Workflow:Bentoml BentoML Multi Model Composition
- Workflow:Bigscience workshop Petals Distributed Text Generation
- Workflow:Online ml River Drift Adaptive Classification
- Workflow:Apache Dolphinscheduler Datasource Connection Management
Principles
- Principle:ClickHouse ClickHouse Strong IP Types
- Principle:Deepseek ai Janus Prompt Formatting for Generation
- Principle:Openai Openai agents python Agent Level Guardrail Definition
- Principle:Anthropics Anthropic sdk python Thinking Request Execution
- Principle:Apache Dolphinscheduler Workflow Instance Recovery
- Principle:ClickHouse ClickHouse Poco JSON Templating
- Principle:Openai Evals Self Consistency Prompting
- Principle:Bentoml BentoML Model Cleanup
- Principle:Online ml River Tree Node Architecture
- Principle:Tencent Ncnn Dependency Free Build
Implementations
- Implementation:Online ml River Sketch Histogram
- Implementation:Openai Whisper Get Writer
- Implementation:Guardrails ai Guardrails Merge
- Implementation:Apache Hudi HoodieFlinkStreamer Main
- Implementation:Mbzuai oryx Awesome LLM Post training Search Papers
- Implementation:Online ml River Stream Iter Csv
- Implementation:Microsoft Semantic kernel FunctionChoiceBehavior Auto
- Implementation:MaterializeInc Materialize Debug Symbols Uploader
- Implementation:SeleniumHQ Selenium Closure SafeUrl
- Implementation:Sdv dev SDV Download Demo
Heuristics
- Heuristic:Deepseek ai Janus Image Generation Prompt Tips
- Heuristic:FMInference FlexLLMGen Pin Memory Tradeoffs
- Heuristic:Princeton nlp Tree of thought llm Functools Partial Model Binding
- Heuristic:ARISE Initiative Robosuite Hard Reset Vs Soft Reset
- Heuristic:OpenRLHF OpenRLHF vLLM Embedding Resize Warning
- Heuristic:SeleniumHQ Selenium Warning Deprecated HasDownloads GetDownloadableFiles
- Heuristic:Openai Openai agents python Default Max Turns Safety Limit
- Heuristic:Hiyouga LLaMA Factory LoRA DDP Configuration
- Heuristic:Ollama Ollama VRAM Recovery And Scheduling
- Heuristic:Rapidsai Cuml Dask Data Partitioning
Environments
- Environment:Deepset ai Haystack OpenAI API Environment
- Environment:ContextualAI HALOs CUDA 12 1 Training Environment
- Environment:Deepseek ai Janus JanusFlow Diffusers Environment
- Environment:Huggingface Optimum Tensor Parallelization Environment
- Environment:Helicone Helicone Wrangler CLI
- Environment:Arize ai Phoenix Python Runtime
- Environment:Huggingface Diffusers Training Environment
- Environment:Fede1024 Rust rdkafka Kafka Broker Runtime
- Environment:Mistralai Client python Realtime Transcription Environment
- Environment:Sgl project Sglang CPU