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:Lance format Lance Vector Search Pipeline
- Workflow:Langgenius Dify Plugin Installation and Configuration
- Workflow:DataExpert io Data engineer handbook PySpark Job Testing
- Workflow:Mistralai Client python Streaming Chat Completion
- Workflow:Ggml org Llama cpp Interactive Chat
- Workflow:AUTOMATIC1111 Stable diffusion webui LoRA network application
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:LLMBook zh LLMBook zh github io Supervised Finetuning
- Workflow:Open compass VLMEvalKit Video Benchmark Evaluation
- Workflow:Protectai Llm guard API Server Deployment
Principles
- Principle:Apache Paimon Schema Alignment
- Principle:Fastai Fastbook Tabular Preprocessing
- Principle:FMInference FlexLLMGen CuBLAS Inference Wrappers
- Principle:AnswerDotAI RAGatouille Hard Negative Mining
- Principle:Spcl Graph of thoughts Document Merging Response Parsing
- Principle:Huggingface Trl GRPO Model Saving
- Principle:Scikit learn Scikit learn Discriminant Analysis
- Principle:Mlc ai Web llm Function Calling Model Selection
- Principle:DataTalksClub Data engineering zoomcamp Dbt Intermediate Layer
- Principle:Neuml Txtai Document Preparation
Implementations
- Implementation:Mit han lab Llm awq Real quantize model weight
- Implementation:Facebookresearch Habitat lab BaseILTrainer
- Implementation:Datahub project Datahub MetadataResponseFuture
- Implementation:Cohere ai Cohere python API Key From Environment
- Implementation:Ray project Ray MessagePackSerializer Encode
- Implementation:Infiniflow Ragflow ThemeProvider Component
- Implementation:Apache Kafka Git Push Remote
- Implementation:Guardrails ai Guardrails DocumentStore
- Implementation:Cohere ai Cohere python HttpResponse
- Implementation:NVIDIA NeMo Curator Nightly Benchmark Config
Heuristics
- Heuristic:DataTalksClub Data engineering zoomcamp Dbt Materialization Strategy
- Heuristic:BerriAI Litellm SSL Cipher Optimization
- Heuristic:Haotian liu LLaVA Tokenizer Version Offset Correction
- Heuristic:Apache Beam Executor Shutdown Ordering
- Heuristic:Openai Whisper KV Cache Optimization
- Heuristic:DevExpress Testcafe MacOS Browser Launch Serialization
- Heuristic:Alibaba MNN Memory Mode Selection
- Heuristic:Microsoft Onnxruntime Threading Configuration Tips
- Heuristic:SqueezeAILab ETS Softmax Temperature Tuning
- Heuristic:OpenBMB UltraFeedback Score 10 Anomaly Correction
Environments
- Environment:ArroyoSystems Arroyo PostgreSQL Database
- Environment:Mlc ai Mlc llm CUDA GPU Environment
- Environment:ClickHouse ClickHouse Systemd Runtime
- Environment:Lm sys FastChat GPU CUDA Inference
- Environment:Datajuicer Data juicer GPU CUDA Environment
- Environment:Apache Dolphinscheduler Java Runtime
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:Openai Openai python Voice Helpers
- Environment:TobikoData Sqlmesh Snowflake Connection
- Environment:Datajuicer Data juicer Python Runtime Environment