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:Facebookresearch Habitat lab PointNav PPO Training
- Workflow:Microsoft Onnxruntime Train Convert Predict
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
- Workflow:Interpretml Interpret Blackbox Model Explanation
- Workflow:Mit han lab Llm awq AWQ Model Quantization
- Workflow:Onnx Onnx Reference Evaluation
- Workflow:Risingwavelabs Risingwave CDC Data Replication
- Workflow:Huggingface Optimum Model Export
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:Google research Deduplicate text datasets Cross dataset deduplication
Principles
- Principle:Sdv dev SDV Diagnostic Reporting
- Principle:Pyro ppl Pyro MCMC Numerical Methods
- Principle:Huggingface Datasets WebDataset Building
- Principle:Triton inference server Server Server Launch
- Principle:Truera Trulens LangChain App Wrapping
- Principle:Heibaiying BigData Notes Spark Aggregation and Join
- Principle:AUTOMATIC1111 Stable diffusion webui Model Architecture Abstraction
- Principle:Mit han lab Llm awq Calibration Data Preparation
- Principle:Togethercomputer Together python Chat Completion Request
- Principle:Microsoft Semantic kernel Vector Store Collection Setup
Implementations
- Implementation:FlowiseAI Flowise DocStoreInputHandler
- Implementation:Alibaba MNN MNN Low Memory Runtime
- Implementation:Facebookresearch Audiocraft AudioEffects
- Implementation:Unslothai Unsloth RawTextDataLoader
- Implementation:EvolvingLMMs Lab Lmms eval TUI Web Dependencies
- Implementation:CARLA simulator Carla StreamingEndPoint
- Implementation:CARLA simulator Carla Traffic Generation Script
- Implementation:NVIDIA DALI Operator Trace Tests
- Implementation:Tensorflow Tfjs Tensorflowjs Converter CLI
- Implementation:Google deepmind Mujoco MJX Solver
Heuristics
- Heuristic:Puppeteer Puppeteer Chrome Default Launch Arguments
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
- Heuristic:Hiyouga LLaMA Factory Mixed Precision Training Tips
- Heuristic:MaterializeInc Materialize Docker Image Cache Lookup
- Heuristic:Apache Shardingsphere Version Cleanup After Switch
- Heuristic:ArroyoSystems Arroyo Checkpoint Interval Tuning
- Heuristic:Intel Ipex llm NF4 Quantization Best Practice
- Heuristic:ARISE Initiative Robomimic Rollout Horizon Selection
- Heuristic:Obss Sahi Warning Deprecated Legacy NMS
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
Environments
- Environment:Shiyu coder Kronos Qlib Data Environment
- Environment:Volcengine Verl CUDA GPU Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:TobikoData Sqlmesh Web UI Stack
- Environment:ARISE Initiative Robomimic HuggingFace Hub Dependencies
- Environment:Facebookresearch Habitat lab HITL Runtime Environment
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Volcengine Verl Ray Distributed Environment
- Environment:Lance format Lance SIMD And Platform Requirements