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:Apache Dolphinscheduler Workflow Failover Recovery
- Workflow:Liu00222 Open Prompt Injection Prompt Injection Experiment
- Workflow:LaurentMazare Tch rs Transfer Learning
- Workflow:Huggingface Transformers Model Benchmarking
- Workflow:Huggingface Transformers PEFT Adapter Integration
- Workflow:Sktime Pytorch forecasting TFT Demand Forecasting
- Workflow:ARISE Initiative Robomimic Hyperparameter Sweep
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:Pytorch Serve LLM Deployment vLLM
Principles
- Principle:Eventual Inc Daft Arrow Export
- Principle:LLMBook zh LLMBook zh github io Bitsandbytes Quantization
- Principle:FMInference FlexLLMGen Fused Transformer Layer CUDA
- Principle:Huggingface Diffusers LoRA Adapter Injection
- Principle:Hpcaitech ColossalAI RAG Deployment
- Principle:Triton inference server Server Ensemble Validation
- Principle:Triton inference server Server Ensemble Pipeline Testing
- Principle:Groq Groq python Client Initialization
- Principle:Apache Paimon Atomic Commit
- Principle:Rapidsai Cuml Regression Evaluation
Implementations
- Implementation:Intel Ipex llm IpexLLM From Model Id
- Implementation:Neuml Txtai Pooling Base
- Implementation:Sdv dev SDV Download Demo
- Implementation:Openai Openai node Jobs Create
- Implementation:Run llama Llama index GraphStore Types
- Implementation:Scikit learn Scikit learn OPTICS
- Implementation:Open compass VLMEvalKit QwenVL
- Implementation:Ggml org Ggml Metal backend api
- Implementation:Mit han lab Llm awq Get prompter
- Implementation:Sgl project Sglang Health And Metrics Endpoints
Heuristics
- Heuristic:Huggingface Alignment handbook Sequence Packing Strategy
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:Scikit learn contrib Imbalanced learn KNeighbors Selection Tips
- Heuristic:Elevenlabs Elevenlabs python VAD vs Manual Commit Strategy
- Heuristic:Isaac sim IsaacGymEnvs DR Setup Only Flag
- Heuristic:Obss Sahi Class Agnostic vs Per Class NMS
- Heuristic:Huggingface Open r1 Reward Function Tuning
- Heuristic:Langgenius Dify Gevent Monkey Patching Order
- Heuristic:Openai Evals Eval Resumption Strategy
- Heuristic:OWASP Www project top 10 for large language model applications Sandbox Containerization Pattern
Environments
- Environment:Vespa engine Vespa FNET Transport Config
- Environment:Heibaiying BigData Notes Kafka 2 2 Environment
- Environment:Vespa engine Vespa Cosign Sigstore Signing
- Environment:InternLM Lmdeploy Python Dependencies
- Environment:Sgl project Sglang ROCm
- Environment:Elevenlabs Elevenlabs python PyAudio
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:Intel Ipex llm RAG LangChain Environment
- Environment:ClickHouse ClickHouse Linux Build Environment
- Environment:Snorkel team Snorkel Dask Distributed