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 with the Leeroopedia MCP setup guide. Let it search docs, build plans, verify code, and diagnose failures on your behalf.
Go end-to-end. Leeroopedia gives your agent the knowledge. Kapso gives it the ability to act on it: research, experiment, and deploy.
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:DataTalksClub Data engineering zoomcamp dlt Data Ingestion
- Workflow:Scikit learn contrib Imbalanced learn SMOTE Resampling Pipeline
- Workflow:FMInference FlexLLMGen HELM Benchmark Evaluation
- Workflow:Sgl project Sglang Online Serving With OpenAI API
- Workflow:OpenBMB UltraFeedback Dataset Construction
- Workflow:Ray project Ray Build and Release Pipeline
- Workflow:Confident ai Deepeval Synthetic Dataset Generation
- Workflow:TobikoData Sqlmesh Dbt project migration
- Workflow:Triton inference server Server LLM Deployment With TRT LLM
- Workflow:Anthropics Anthropic sdk python Tool Use Integration
Principles
- Principle:Langgenius Dify Prompt Template Design
- Principle:Microsoft Autogen Tool Execution Loop
- Principle:Microsoft Semantic kernel RAG Chat Augmentation
- Principle:Groq Groq python Response Model Construction
- Principle:MarketSquare Robotframework browser HTTP Request Execution
- Principle:Ggml org Llama cpp Embedding Computation
- Principle:Openclaw Openclaw Credential Acquisition
- Principle:VainF Torch Pruning YOLO Architecture Adaptation
- Principle:DataTalksClub Data engineering zoomcamp Parquet Data Ingestion
- Principle:Datahub project Datahub V2 Client Setup
Implementations
- Implementation:Google deepmind Mujoco JAX Experimental Custom Call
- Implementation:Kornia Kornia Quaternion
- Implementation:Sgl project Sglang Build Regex From Object
- Implementation:Apache Druid ShowJsonOrStages
- Implementation:Pyro ppl Pyro Einsum Example
- Implementation:Rapidsai Cuml Make Blobs
- Implementation:Apache Druid RuleEditor
- Implementation:TobikoData Sqlmesh Story ModelLineage
- Implementation:Turboderp org Exllamav2 ExLlamaV2DeviceContext
- Implementation:SeleniumHQ Selenium Closure BrowserEvent
Heuristics
- Heuristic:Nautechsystems Nautilus trader Cache Buffer Interval Tuning
- Heuristic:Facebookresearch Habitat lab VER Tuning Guidelines
- Heuristic:Dagster io Dagster Batch Size Tuning
- Heuristic:Tencent Ncnn NMS Threshold Tuning
- Heuristic:Gretelai Gretel synthetics Parallel Generation CUDA Disable
- Heuristic:Apache Spark Partition Sizing Tips
- Heuristic:Langchain ai Langchain Text Splitter Separator Hierarchy
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Huggingface Trl Distributed Device Map Override
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
Environments
- Environment:Eric mitchell Direct preference optimization Python Dependencies
- Environment:Ggml org Llama cpp Python Conversion Environment
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:Alibaba ROLL Megatron Training Environment
- Environment:TA Lib Ta lib python Python Build Environment
- Environment:Zai org CogVideo Video Captioning Environment
- Environment:Apache Kafka Gradle Build Environment
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:Microsoft Semantic kernel DotNet SDK Environment