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:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:Openai Openai python Embeddings Generation
- Workflow:Mbzuai oryx Awesome LLM Post training Awesome List Curation
- Workflow:Facebookresearch Audiocraft EnCodec Compression Training
- Workflow:DataTalksClub Data engineering zoomcamp Spark Batch Processing
- Workflow:DevExpress Testcafe CLI Test Execution
- Workflow:Eric mitchell Direct preference optimization SFT Training
- Workflow:Testtimescaling Testtimescaling github io Automated Citation Tracking
- Workflow:Scikit learn contrib Imbalanced learn SMOTE Resampling Pipeline
- Workflow:Pytorch Serve HuggingFace Transformer Serving
Principles
- Principle:Evidentlyai Evidently Dataset Creation
- Principle:Webdriverio Webdriverio AI Self Healing
- Principle:Haosulab ManiSkill Physics Struct Abstraction
- Principle:Promptfoo Promptfoo Assertion Grading
- Principle:FMInference FlexLLMGen Async IO NVMe Operations
- Principle:Norrrrrrr lyn WAInjectBench LLaVA Training Data Preparation
- Principle:Google deepmind Mujoco Composite Rigid Body
- Principle:Langgenius Dify Database Migrations
- Principle:Norrrrrrr lyn WAInjectBench Dynamic Detector Loading Text
- Principle:Ggml org Llama cpp Server Monitoring
Implementations
- Implementation:Turboderp org Exllamav2 Ext RoPE
- Implementation:Kserve Kserve DenseNet161 ImageClassifier
- Implementation:Infiniflow Ragflow Admin Roles Page
- Implementation:Truera Trulens Otel StackTreeNode
- Implementation:Open compass VLMEvalKit KimiVLAPIWrapper
- Implementation:NVIDIA NeMo Aligner Anneal SDXL
- Implementation:LLMBook zh LLMBook zh github io Get Data DPO
- Implementation:Langfuse Langfuse InMemoryFilterService
- Implementation:Google deepmind Mujoco MjModel from xml path
- Implementation:Speechbrain Speechbrain Prepare Common Voice For Whisper
Heuristics
- Heuristic:Microsoft Agent framework Declaration Only Tools Pattern
- Heuristic:Puppeteer Puppeteer Chrome Default Launch Arguments
- Heuristic:Eric mitchell Direct preference optimization FSDP Batch Size Per GPU
- Heuristic:Obss Sahi Overlap Ratio Selection
- Heuristic:Alibaba ROLL PPO Clipping Defaults
- Heuristic:Liu00222 Open Prompt Injection Attack Effectiveness Hierarchy
- Heuristic:Rapidsai Cuml CUDA Kernel Caching
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:Recommenders team Recommenders TensorFlow Session Ordering
- Heuristic:BerriAI Litellm Batch Size Flush Interval Tuning
Environments
- Environment:Turboderp org Exllamav2 Build Toolchain
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:Apache Beam Portable Runner Environment
- Environment:Heibaiying BigData Notes Java 8 Maven Environment
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:Eric mitchell Direct preference optimization Python Dependencies
- Environment:Huggingface Optimum Tensor Parallelization Environment
- Environment:Haotian liu LLaVA Python CUDA Training Environment
- Environment:Puppeteer Puppeteer Cross Platform Browser Environment
- Environment:Intel Ipex llm XPU Inference Environment