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:HKUDS AI Trader Agent Decision Loop
- Workflow:Groq Groq python Streaming Chat Completion
- Workflow:Facebookresearch Habitat lab Rearrangement HRL Training
- Workflow:Huggingface Transformers Pipeline Inference
- Workflow:Pytorch Serve Model Deployment
- Workflow:Vllm project Vllm Structured Output Generation
- Workflow:Datajuicer Data juicer LLM Powered Data Generation
- Workflow:Kubeflow Pipelines Pipeline Control Flow
- Workflow:AUTOMATIC1111 Stable diffusion webui Checkpoint merging
- Workflow:Nautechsystems Nautilus trader Backtest with BacktestEngine
Principles
- Principle:Huggingface Datatrove Job Status Monitoring
- Principle:ClickHouse ClickHouse Glibc Symbol Replacement
- Principle:NVIDIA NeMo Curator Text Cleaning and Normalization
- Principle:Neuml Txtai Agent Task Execution
- Principle:Microsoft Onnxruntime Result Processing
- Principle:Ollama Ollama Local Manifest Management
- Principle:Huggingface Datasets Hub Config Verification
- Principle:Run llama Llama index Text Chunking
- Principle:Haosulab ManiSkill Gymnasium Wrappers
- Principle:Dagster io Dagster Custom Resource Pattern
Implementations
- Implementation:SeldonIO Seldon core Seldon Pipeline Load And Status
- Implementation:NVIDIA DALI Fn Readers Video
- Implementation:Scikit learn Scikit learn AgglomerationTransform
- Implementation:Treeverse LakeFS Java SDK Model CompletePresignMultipartUpload
- Implementation:Turboderp org Exllamav2 Measure Quant
- Implementation:Infiniflow Ragflow QueryBase
- Implementation:Google deepmind Mujoco Studio App
- Implementation:Guardrails ai Guardrails AsyncValidatorService
- Implementation:Speechbrain Speechbrain Hparams Switchboard Transformer LM
- Implementation:Huggingface Datatrove LineStats
Heuristics
- Heuristic:Wandb Weave Sentinel Value Handling
- Heuristic:NVIDIA NeMo Aligner Warning Deprecated Repository
- Heuristic:Infiniflow Ragflow Hybrid Search Fallback Strategy
- Heuristic:Fede1024 Rust rdkafka Manual Offset Store Pattern
- Heuristic:Huggingface Peft LoRA Initialization Strategy Selection
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
- Heuristic:FlagOpen FlagEmbedding Same Dataset Batching Tip
- Heuristic:Openai Evals Chat Format Recommendation
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:Recommenders team Recommenders Test Timing Budgets
Environments
- Environment:Huggingface Transformers PEFT Adapter Env
- Environment:Ucbepic Docetl Docker Deployment
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:Bitsandbytes foundation Bitsandbytes CUDA GPU Runtime
- Environment:Langchain ai Langchain OpenAI API Credentials
- Environment:Treeverse LakeFS Web UI Environment
- Environment:Openai Openai python Voice Helpers
- Environment:Tensorflow Serving Python Client Environment
- Environment:Treeverse LakeFS S3 Gateway Test Environment
- Environment:Webdriverio Webdriverio Browser Driver Environment