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 Audiocraft MusicGen Text To Music Inference
- Workflow:Haosulab ManiSkill Imitation Learning Pipeline
- Workflow:Microsoft Agent framework Multi Agent Concurrent Orchestration
- Workflow:Gretelai Gretel synthetics DGAN Timeseries Generation
- Workflow:Dagster io Dagster ML Pipeline
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Ggml org Llama cpp Speculative Decoding
- Workflow:SeleniumHQ Selenium Browser Session Setup
- Workflow:Langfuse Langfuse Evaluation pipeline
- Workflow:Microsoft Playwright End to end test authoring
Principles
- Principle:Huggingface Optimum Parameter Metadata Initialization
- Principle:Open compass VLMEvalKit Video Inference Orchestration
- Principle:Haotian liu LLaVA Custom Dataset Formatting
- Principle:Nautechsystems Nautilus trader Historical Data Wrangling
- Principle:Puppeteer Puppeteer Dynamic Content Waiting
- Principle:MaterializeInc Materialize Scalability Regression Testing
- Principle:Tensorflow Serving Version Policy Configuration
- Principle:Microsoft LoRA Low Rank Layer Replacement
- Principle:Avhz RustQuant Numerical Integration
- Principle:Turboderp org Exllamav2 Bit Allocation Optimization
Implementations
- Implementation:Mlflow Mlflow Scorer Class
- Implementation:Tencent Ncnn YOLO World Example
- Implementation:Online ml River Base Estimator
- Implementation:Openai Whisper Log Mel Spectrogram
- Implementation:Arize ai Phoenix Generated V1 Types
- Implementation:OpenGVLab InternVL GPT Review Evaluation
- Implementation:Online ml River Tree Splitter Base
- Implementation:Guardrails ai Guardrails Guard Use Custom Validator
- Implementation:Onnx Onnx Version Converter Convert Version
- Implementation:SeleniumHQ Selenium Closure Testing TestCase
Heuristics
- Heuristic:Infiniflow Ragflow Reranking Weight Tuning
- Heuristic:LLMBook zh LLMBook zh github io Deduplication Ngram Threshold
- Heuristic:Recommenders team Recommenders TensorFlow Session Ordering
- Heuristic:Huggingface Trl Gradient Checkpointing Use Reentrant
- Heuristic:Turboderp org Exllamav2 Paged Cache Configuration
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:Mbzuai oryx Awesome LLM Post training Checkpoint Every 3 Papers
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:TA Lib Ta lib python Compatibility Mode Switching
- Heuristic:Mlc ai Mlc llm FlashInfer KV Cache Fallback
Environments
- Environment:MarketSquare Robotframework browser Python Runtime
- Environment:Sgl project Sglang Multi Platform Accelerators
- Environment:Avhz RustQuant Rust Stable
- Environment:Kubeflow Kubeflow Kubernetes Cluster Environment
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:Onnx Onnx Python Runtime Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Requests
- Environment:Openclaw Openclaw State Directory And Credentials
- Environment:Arize ai Phoenix OpenTelemetry SDK
- Environment:Danijar Dreamerv3 JAX CUDA