Main Page
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:Alibaba MNN Model Compression
- Workflow:Volcengine Verl Multi Turn Tool Use Training
- Workflow:TA Lib Ta lib python Basic Indicator Computation
- Workflow:Apache Beam Twister2 Batch Execution
- Workflow:Helicone Helicone Local Development Setup
- Workflow:Unslothai Unsloth Vision Model Finetuning
- Workflow:Langgenius Dify RAG Pipeline Development
- Workflow:Unstructured IO Unstructured Performance Profiling
- Workflow:Mlfoundations Open flamingo Few Shot Evaluation
- Workflow:Spotify Luigi Hadoop MapReduce Pipeline
Principles
- Principle:Sktime Pytorch forecasting KAN Architecture
- Principle:Eventual Inc Daft Batch UDF
- Principle:Duckdb Duckdb Fast Number Parsing
- Principle:Pyro ppl Pyro Effect Handler System
- Principle:CrewAIInc CrewAI Task Definition
- Principle:Fede1024 Rust rdkafka Crate Public API Surface
- Principle:Princeton nlp Tree of thought llm DFS Tree Search
- Principle:NVIDIA NeMo Curator Connected Component Analysis
- Principle:ClickHouse ClickHouse Optimized Memcpy
- Principle:Iterative Dvc Terminal Table Rendering
Implementations
- Implementation:Protectai Llm guard Input Regex
- Implementation:Unstructured IO Unstructured ChunkingOptions
- Implementation:Nightwatchjs Nightwatch Nightwatch CLI Init
- Implementation:Microsoft DeepSpeedExamples Fuse LoRA
- Implementation:Ollama Ollama XTools WebFetch
- Implementation:Nightwatchjs Nightwatch Page Commands Interface
- Implementation:Evidentlyai Evidently Dashboard Panels
- Implementation:Treeverse LakeFS Java SDK Model IcebergPushRequest
- Implementation:Spotify Luigi Retcodes
- Implementation:Infiniflow Ragflow Admin Login Page
Heuristics
- Heuristic:Mlc ai Mlc llm Optimization Level Selection
- Heuristic:Onnx Onnx Warning Deprecated InlineSelectedFunctions
- Heuristic:Run llama Llama index Batch Eval Retry Strategy
- Heuristic:Diagram of thought Diagram of thought Strict Vs Flexible Critic Rigor
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
- Heuristic:NVIDIA TransformerEngine Build Optimization Tips
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:Langchain ai Langgraph Stream Mode Selection
- Heuristic:NVIDIA TransformerEngine Sequence Length Alignment
- Heuristic:Bitsandbytes foundation Bitsandbytes Outlier Threshold Detection
Environments
- Environment:InternLM Lmdeploy Build From Source
- Environment:Huggingface Datasets TensorFlow Integration
- Environment:Farama Foundation Gymnasium Python 3 10 Runtime
- Environment:Mlflow Mlflow GPU System Metrics Environment
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:Deepspeedai DeepSpeed XPU Environment
- Environment:Getgauge Taiko Linux System Libraries
- Environment:Hiyouga LLaMA Factory Core Python GPU Environment
- Environment:Apache Flink Node Build Environment
- Environment:SeldonIO Seldon core Kubernetes Cluster Environment