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:NVIDIA TransformerEngine Accelerate HF Llama With TE
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:Tensorflow Tfjs Sequential Model Training
- Workflow:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:Unstructured IO Unstructured Document Partitioning
- Workflow:Arize ai Phoenix Prompt Management Pipeline
- Workflow:Isaac sim IsaacGymEnvs Factory Assembly Training
- Workflow:OpenRLHF OpenRLHF Reward Model Training
- Workflow:ARISE Initiative Robosuite Domain Randomization Training
- Workflow:Microsoft Onnxruntime Distributed Model Training
Principles
- Principle:Apache Kafka Source Artifact Building
- Principle:Sdv dev SDV Single Table Data Sampling
- Principle:SeleniumHQ Selenium Element Caching Strategy
- Principle:Ollama Ollama GGUF Model Conversion Llama4
- Principle:Microsoft Agent framework Executor Definition
- Principle:Recommenders team Recommenders Spark Evaluation Metrics
- Principle:Unstructured IO Unstructured Embedding Provider Interface
- Principle:Huggingface Diffusers Video Pipeline Selection
- Principle:Risingwavelabs Risingwave Iceberg Table Maintenance
- Principle:CrewAIInc CrewAI Tool Execution And Monitoring
Implementations
- Implementation:Cohere ai Cohere python Text Preparation Pattern
- Implementation:Facebookresearch Habitat lab Observations to image
- Implementation:Ggml org Llama cpp Llama Model Quantize Params
- Implementation:Ggml org Llama cpp Batched Bench
- Implementation:Kserve Kserve InferenceGraph CRD Spec
- Implementation:InternLM Lmdeploy ModelRequest
- Implementation:Explodinggradients Ragas AgentGoalAccuracy Metric
- Implementation:Mlflow Mlflow Predict Function Interface
- Implementation:BerriAI Litellm Passthrough API
- Implementation:Ollama Ollama Imagegen Tokenizer
Heuristics
- Heuristic:Nautechsystems Nautilus trader Inflight Order Check Threshold
- Heuristic:Microsoft Autogen Agent Thread Safety
- Heuristic:BerriAI Litellm Connection Pooling Memory Management
- Heuristic:Triton inference server Server Server Default Configuration
- Heuristic:BerriAI Litellm Retry Backoff Strategy
- Heuristic:PacktPublishing LLM Engineers Handbook Token Window Safety Margin
- Heuristic:Obss Sahi Overlap Ratio Selection
- Heuristic:Openai Openai node Browser Safety Guard
- Heuristic:Apache Shardingsphere Worker ID Reservation Strategy
- Heuristic:Nautechsystems Nautilus trader Streaming Mode For Large Backtests
Environments
- Environment:Shiyu coder Kronos Qlib Data Environment
- Environment:NVIDIA NeMo Curator RAPIDS GPU Stack
- Environment:Ggml org Llama cpp Python Conversion Environment
- Environment:Datahub project Datahub Python 3 10 Ingestion Environment
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Pyro ppl Pyro Distributed Training
- Environment:Truera Trulens LangChain LangGraph Environment
- Environment:Huggingface Datatrove Inference GPU Environment
- Environment:Tensorflow Tfjs Browser Runtime
- Environment:Intel Ipex llm XPU Inference Environment