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:Onnx Onnx Version Conversion
- Workflow:Evidentlyai Evidently LLM Evaluation Monitoring
- Workflow:Lm sys FastChat ShareGPT Data Pipeline
- Workflow:Microsoft Semantic kernel Plugin Integration And Function Calling
- Workflow:Kornia Kornia Image Stitching Panorama
- Workflow:Langchain ai Langchain Release Process
- Workflow:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:Alibaba ROLL RLVR Training Pipeline
- Workflow:Microsoft LoRA LoRA Integration
- Workflow:Haotian liu LLaVA Two Stage Pretraining and Finetuning
Principles
- Principle:Anthropics Anthropic sdk python API Resource Pattern
- Principle:Langchain ai Langgraph Agent Execution
- Principle:Microsoft Agent framework Sample Validation
- Principle:Microsoft BIPIA Results Analysis
- Principle:Huggingface Optimum Framework Detection
- Principle:Huggingface Datasets NumPy Formatting
- Principle:Sktime Pytorch forecasting NHiTS Architecture
- Principle:Datajuicer Data juicer Operator Package Registration
- Principle:Webdriverio Webdriverio Test Result Reporting
- Principle:Protectai Llm guard Output Scanning
Implementations
- Implementation:SqueezeAILab ETS Grade Answer
- Implementation:Microsoft Onnxruntime Module TrainStep
- Implementation:Tensorflow Serving Docker Build Serving Image
- Implementation:Huggingface Datasets CsvDatasetReader
- Implementation:Alibaba MNN Protobuf Wire Format H
- Implementation:Google deepmind Mujoco WASM Bindings Template
- Implementation:Apache Kafka Broker Log4j2 Configuration
- Implementation:Microsoft Autogen Studio Web Dependencies
- Implementation:Vllm project Vllm CPU Fused MoE
- Implementation:Kserve Kserve Tag Based Routing Validation
Heuristics
- Heuristic:LaurentMazare Tch rs Device Fallback Pattern
- Heuristic:Hpcaitech ColossalAI Empty Cache Between Phases
- Heuristic:Bigscience workshop Petals Batch Splitting Threshold
- Heuristic:OpenGVLab InternVL Loss Reduction Strategy
- Heuristic:Fede1024 Rust rdkafka Cooperative Rebalance Protocol
- Heuristic:Fede1024 Rust rdkafka Multi Version Dependency Hazard
- Heuristic:Openai CLIP Template Ensemble For Zero Shot
- Heuristic:Huggingface Open r1 Distributed Training Configuration
- Heuristic:Langgenius Dify Credential Sanitization In API Responses
- Heuristic:Apache Airflow Task Dependency Isolation
Environments
- Environment:Speechbrain Speechbrain Speech Enhancement Dependencies
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:FlowiseAI Flowise Node Runtime Environment
- Environment:Google deepmind Dm control GLFW Desktop Rendering
- Environment:Ggml org Llama cpp CUDA GPU Environment
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Microsoft Semantic kernel OpenAI API Environment
- Environment:Microsoft Autogen Studio Server Environment