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:Pola rs Polars SQL Query Interface
- Workflow:Eventual Inc Daft Distributed UDF Processing
- Workflow:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:Lance format Lance Vector Search Pipeline
- Workflow:Pyro ppl Pyro VAE Training
- Workflow:Langgenius Dify Knowledge Base Creation
- Workflow:Volcengine Verl Supervised Fine Tuning
- Workflow:Googleapis Python genai Image Generation Pipeline
- Workflow:Nautechsystems Nautilus trader Strategy development
- Workflow:LLMBook zh LLMBook zh github io Data Preprocessing Pipeline
Principles
- Principle:Datajuicer Data juicer Data Mapping Transformation
- Principle:Bentoml BentoML Cloud Authentication
- Principle:ArroyoSystems Arroyo Pipeline Shutdown
- Principle:VainF Torch Pruning Pruned Model Serialization
- Principle:Huggingface Optimum Reversible Transformation
- Principle:Ggml org Llama cpp Encoding Utilities
- Principle:Huggingface Datasets Eval Dataset Building
- Principle:Langchain ai Langgraph UI Component Management
- Principle:Deepset ai Haystack Chat Prompt Templating
- Principle:SeleniumHQ Selenium Page Object Interaction Methods
Implementations
- Implementation:Kserve Kserve OpenAI Completions API
- Implementation:Online ml River Multiclass OneVsOne
- Implementation:Open compass VLMEvalKit VDC Utils
- Implementation:Risingwavelabs Risingwave Relation Graph Page
- Implementation:Bitsandbytes foundation Bitsandbytes Adam8bit
- Implementation:InternLM Lmdeploy Gemm ThreadMap
- Implementation:Cohere ai Cohere python GenerateStreamedResponse Union
- Implementation:Allenai Open instruct Layer Init
- Implementation:Evidentlyai Evidently UI Backport
- Implementation:Haosulab ManiSkill Sim2RealEnv
Heuristics
- Heuristic:Anthropics Anthropic sdk python Streaming For Long Requests
- Heuristic:DataExpert io Data engineer handbook Flink Checkpointing Interval Tuning
- Heuristic:Fastai Fastbook Embedding Size Rule
- Heuristic:LMCache LMCache Chunk Size And Default Config
- Heuristic:Scikit learn Scikit learn Convergence Warning Handling
- Heuristic:LLMBook zh LLMBook zh github io DPO Beta Hyperparameter
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:Alibaba MNN GPU Tuning Modes
- Heuristic:Langgenius Dify SQL Escape Backslash First
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
Environments
- Environment:Ray project Ray Docker GPU Environment
- Environment:Bentoml BentoML Python Runtime
- Environment:Apache Flink Python PyFlink Environment
- Environment:Vllm project Vllm AWS ECR
- Environment:Apache Hudi Docker Demo Environment
- Environment:Promptfoo Promptfoo SQLite Database
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Microsoft Semantic kernel ONNX CUDA Environment
- Environment:EvolvingLMMs Lab Lmms eval Server Mode Environment
- Environment:Gretelai Gretel synthetics Python Base Environment