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:Infiniflow Ragflow Chat Application Setup
- Workflow:ChenghaoMou Text dedup Benchmark Evaluation
- Workflow:Cypress io Cypress Binary Build and Release
- Workflow:Speechbrain Speechbrain Speech Enhancement Training
- Workflow:Datahub project Datahub Java SDK V2 Entity Management
- Workflow:Cohere ai Cohere python Text Embedding
- Workflow:HKUDS AI Trader Data Pipeline
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:FlowiseAI Flowise Chatbot Deployment
- Workflow:Ucbepic Docetl Pipeline Optimization
Principles
- Principle:Sdv dev SDV Cardinality Analysis
- Principle:LLMBook zh LLMBook zh github io SFT Model Loading
- Principle:OpenHands OpenHands Compensating Transaction
- Principle:Haotian liu LLaVA Environment Setup
- Principle:Pytorch Serve GRPC Communication
- Principle:Lucidrains X transformers Hybrid Discrete Continuous Tokens
- Principle:Farama Foundation Gymnasium Array Backend Conversion
- Principle:Speechbrain Speechbrain Conventional Enhancement Training
- Principle:LaurentMazare Tch rs JIT Forward Pass
- Principle:Apache Paimon Lance Predicate Pushdown
Implementations
- Implementation:Google deepmind Mujoco Engine Util Spatial
- Implementation:Tencent Ncnn YOLO11 OBB Example
- Implementation:Axolotl ai cloud Axolotl Load Datasets
- Implementation:Google deepmind Dm control Composer Environment For Soccer
- Implementation:Open compass VLMEvalKit SArena DINO Score
- Implementation:Open compass VLMEvalKit MMHelix Constants
- Implementation:Microsoft LoRA Run Generation
- Implementation:Helicone Helicone SSO Page
- Implementation:DataTalksClub Data engineering zoomcamp Dlt Loading Method Selection
- Implementation:Deepspeedai DeepSpeed DeepSpeedEngine Checkpoint
Heuristics
- Heuristic:Microsoft Agent framework Tool Approval Mode Production
- Heuristic:Openai Openai agents python Default Max Turns Safety Limit
- Heuristic:Openai CLIP Class Name Curation
- Heuristic:FlowiseAI Flowise Heap Memory Configuration
- Heuristic:Deepspeedai DeepSpeed Sequence Parallel PyTorch Version
- Heuristic:Haosulab ManiSkill Initial Pose Performance
- Heuristic:ArroyoSystems Arroyo Async UDF Concurrency
- Heuristic:Langfuse Langfuse ClickHouse FINAL Skip Optimization
- Heuristic:NVIDIA TransformerEngine FP8 Recipe Auto Selection
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Image Size Multiple of Four
Environments
- Environment:Nautechsystems Nautilus trader Databento API Credentials
- Environment:MarketSquare Robotframework browser Python Runtime
- Environment:Apache Kafka JVM Runtime Environment
- Environment:Langgenius Dify Credentials And Env Vars
- Environment:Duckdb Duckdb CMake Build Toolchain
- Environment:HKUDS AI Trader API Credentials
- Environment:HKUDS AI Trader MCP Services
- Environment:Pyro ppl Pyro Python PyTorch Core
- Environment:Shiyu coder Kronos HuggingFace Hub Access
- Environment:Triton inference server Server TRT LLM Deployment