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:Ollama Ollama Custom Model Creation
- Workflow:Openai Openai agents python Human In The Loop Approval
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Mlfoundations Open flamingo Distributed Training
- Workflow:SeleniumHQ Selenium Selenium Grid Deployment
- Workflow:Microsoft Playwright API testing
- Workflow:Haifengl Smile Nearest Neighbor Search
- Workflow:TA Lib Ta lib python Abstract API Usage
- Workflow:Datajuicer Data juicer Custom Operator Development
- Workflow:DataExpert io Data engineer handbook Dimensional Data Modeling Environment Setup
Principles
- Principle:Iterative Dvc Cache Transfer
- Principle:ClickHouse ClickHouse Server Package Configuration
- Principle:MaterializeInc Materialize Pipeline YAML Generation
- Principle:Tensorflow Serving Request Logging
- Principle:Langfuse Langfuse Prompt Dependency Graph
- Principle:TobikoData Sqlmesh Dbt Project Assessment
- Principle:Onnx Onnx Model Loading
- Principle:Deepspeedai DeepSpeed CPU Communication Backends
- Principle:Langfuse Langfuse Framework Detection and Type Mapping
- Principle:Haotian liu LLaVA GPT Review Aggregation
Implementations
- Implementation:Elevenlabs Elevenlabs python ChapterSnapshotResponse
- Implementation:Mlfoundations Open flamingo Filter no caption or no image
- Implementation:OpenHands OpenHands SlackManager
- Implementation:Datajuicer Data juicer VideoResolutionFilter
- Implementation:Scikit learn Scikit learn LossFunction
- Implementation:Scikit learn Scikit learn UnsupervisedClusterMetrics
- Implementation:ClickHouse ClickHouse BorrowedObjectPool
- Implementation:Run llama Llama index PydanticOutputParser
- Implementation:SeleniumHQ Selenium PageMargin
- Implementation:ClickHouse ClickHouse Clickhouse Local Query
Heuristics
- Heuristic:Microsoft BIPIA BF16 Compute Capability Check
- Heuristic:Facebookresearch Audiocraft Codebook Dead Code Expiration
- Heuristic:Deepseek ai Janus CFG Weight Tuning
- Heuristic:Liu00222 Open Prompt Injection Cosine Similarity Segmentation Threshold
- Heuristic:Trailofbits Fickling Injection Mode Selection
- Heuristic:ARISE Initiative Robomimic Rollout Horizon Selection
- Heuristic:VainF Torch Pruning Pruning Ratio vs Parameter Ratio
- Heuristic:Kornia Kornia Avoid Inplace Ops Compile
- Heuristic:LLMBook zh LLMBook zh github io Greedy Decoding Temperature Zero
- Heuristic:Langchain ai Langchain Error Context Preservation
Environments
- Environment:Marker Inc Korea AutoRAG Python 3 10 Runtime
- Environment:NVIDIA DALI TensorFlow Environment
- Environment:Openai Openai agents python Memory Extensions Dependencies
- Environment:Vllm project Vllm Environment Variables
- Environment:Sgl project Sglang CUDA GPU Runtime
- Environment:Mlc ai Mlc llm OpenCL Android Environment
- Environment:DataExpert io Data engineer handbook Flink Kafka Docker Environment
- Environment:Huggingface Open r1 Slurm Cluster
- Environment:Microsoft Onnxruntime Distributed Training Environment
- Environment:Openai Evals Optional Provider APIs