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:Tencent Ncnn Vulkan GPU Accelerated Inference
- Workflow:Huggingface Alignment handbook SFT DPO Alignment Pipeline
- Workflow:DistrictDataLabs Yellowbrick Feature Analysis and Selection
- Workflow:CarperAI Trlx RLHF Summarization Pipeline
- Workflow:CARLA simulator Carla Simulation Setup and First Steps
- Workflow:Puppeteer Puppeteer Web Scraping And Interaction
- Workflow:Turboderp org Exllamav2 Multimodal Vision Inference
- Workflow:EvolvingLMMs Lab Lmms eval End to End Evaluation
- Workflow:Deepspeedai DeepSpeed Inference Engine Optimization
- Workflow:Microsoft Semantic kernel Kernel Setup And Chat Completion
Principles
- Principle:PacktPublishing LLM Engineers Handbook Supervised Finetuning
- Principle:Interpretml Interpret Morris Sensitivity Analysis
- Principle:ArroyoSystems Arroyo Connection Profile Management
- Principle:Spcl Graph of thoughts Sorting Response Parsing
- Principle:Scikit learn contrib Imbalanced learn Balanced Bagging
- Principle:Ollama Ollama Modelfile Format
- Principle:Unstructured IO Unstructured Document Partitioning
- Principle:Webdriverio Webdriverio MonadPattern
- Principle:Deepseek ai Janus Image Post Processing
- Principle:Junyanz Pytorch CycleGAN and pix2pix Pretrained Model Download
Implementations
- Implementation:Scikit learn Scikit learn FetchSpeciesDistributions
- Implementation:Interpretml Interpret DetermineLinkFunction
- Implementation:PrefectHQ Prefect DataAnalysis Output Model
- Implementation:LaurentMazare Tch rs GymEnv
- Implementation:FlowiseAI Flowise Docker Compose Queue Prebuilt
- Implementation:Teamcapybara Capybara Html5 Drag
- Implementation:InternLM Lmdeploy Gateway
- Implementation:Heibaiying BigData Notes DataFrame Transformation API
- Implementation:Marker Inc Korea AutoRAG Evaluator Init
- Implementation:NVIDIA NeMo Curator MinHashStage
Heuristics
- Heuristic:Hpcaitech ColossalAI Empty Cache Between Phases
- Heuristic:Mlc ai Mlc llm Engine Mode Selection
- Heuristic:Apache Kafka Unknown Record Type Upgrade Safety
- Heuristic:Marker Inc Korea AutoRAG Data Format Requirements
- Heuristic:Langgenius Dify Gevent Monkey Patching Order
- Heuristic:Deepseek ai Janus CFG Weight Tuning
- Heuristic:Groq Groq python Retry Backoff Strategy
- Heuristic:Obss Sahi Auto Slice Resolution
- Heuristic:ChenghaoMou Text dedup Bloom Filter Single Process
- Heuristic:Mlc ai Mlc llm Metal KV Cache Capacity Limit
Environments
- Environment:TobikoData Sqlmesh Dbt Compatibility
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Hiyouga LLaMA Factory Core Python GPU Environment
- Environment:MaterializeInc Materialize Buildkite CI Runtime
- Environment:Sail sg LongSpec Training Environment
- Environment:OWASP Www project top 10 for large language model applications PR Description Generator Runtime
- Environment:EvolvingLMMs Lab Lmms eval GPU Compute Environment
- Environment:Microsoft Onnxruntime Sklearn Conversion Environment
- Environment:Bitsandbytes foundation Bitsandbytes HPU Gaudi Runtime
- Environment:Alibaba ROLL vLLM Inference Environment