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:Heibaiying BigData Notes Hive Data Warehouse Operations
- Workflow:Openai Openai agents python Tool Integrated Agent
- Workflow:Langchain ai Langchain Release Process
- Workflow:Cohere ai Cohere python Text Embedding
- Workflow:Volcengine Verl PPO Training With Reward Model
- Workflow:Apache Beam Dataflow Streaming Execution
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:Nightwatchjs Nightwatch E2E Test Authoring
- Workflow:Pyro ppl Pyro Discrete Enumeration
- Workflow:Lm sys FastChat Distributed Model Serving
Principles
- Principle:Langgenius Dify Segment Management
- Principle:Haosulab ManiSkill Trajectory Replay Conversion
- Principle:Apache Beam Transform Override Application Twister2
- Principle:Fede1024 Rust rdkafka Mock Client Configuration
- Principle:Huggingface Datatrove Media Filtering Framework
- Principle:Guardrails ai Guardrails Pydantic Schema Definition
- Principle:Princeton nlp Tree of thought llm BFS Tree Search
- Principle:ArroyoSystems Arroyo Connection Testing
- Principle:Ollama Ollama Architecture Detection
- Principle:Apache Beam Computation Configuration
Implementations
- Implementation:Huggingface Transformers Modular Model Converter
- Implementation:Interpretml Interpret Powerlift InsecureDocker
- Implementation:Lance format Lance BytePack
- Implementation:Speechbrain Speechbrain Tacotron2 Inference Pipeline
- Implementation:Ucbepic Docetl ExperimentEvalUtils
- Implementation:PacktPublishing LLM Engineers Handbook Create Sagemaker Execution Role
- Implementation:NVIDIA NeMo Aligner Anneal SDXL
- Implementation:Huggingface Datasets Dataset To Tf Dataset
- Implementation:Hpcaitech ColossalAI ChineseTextSplitter
- Implementation:Scikit learn Scikit learn Encode
Heuristics
- Heuristic:Microsoft LoRA Selective LoRA QV Only
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Apache Flink Hadoop Thread Safety Mutexes
- Heuristic:Allenai Open instruct Pre Init Torch Distributed
- Heuristic:Volcengine Verl Sequence Length Balancing
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
- Heuristic:Spcl Graph of thoughts Budget Gated Benchmark Execution
- Heuristic:Mlc ai Mlc llm FlashInfer KV Cache Fallback
- Heuristic:Vibrantlabsai Ragas Nest Asyncio Uvloop Compatibility
- Heuristic:Iterative Dvc Path Performance Optimization
Environments
- Environment:Vllm project Vllm AArch64 CPU
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:OpenBMB UltraFeedback Python GPU Environment
- Environment:Huggingface Trl PEFT LoRA Environment
- Environment:Helicone Helicone Python ClickHouse Migrations
- Environment:Apache Paimon Python Core Runtime
- Environment:Avhz RustQuant Rust Stable
- Environment:Helicone Helicone Cloudflare Workers Runtime
- Environment:Triton inference server Server Docker Container Build
- Environment:Openai Openai node Node 20 Runtime