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:InternLM Lmdeploy LLM Offline Batch Inference
- Workflow:Huggingface Alignment handbook Multi Stage Post Training
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:VainF Torch Pruning LLM Structural Pruning
- Workflow:Mage ai Mage ai Building a New Destination Connector
- Workflow:Langfuse Langfuse Trace ingestion pipeline
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Translation
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:ClickHouse ClickHouse Running Stateless Tests
- Workflow:Cypress io Cypress CI Pipeline Integration
Principles
- Principle:Onnx Onnx Model Inspection
- Principle:Diagram of thought Diagram of thought Prompt Template Selection
- Principle:Apache Flink PyFlink Build Distribution
- Principle:Astronomer Astronomer cosmos Operator Arguments Configuration
- Principle:Ggml org Llama cpp Multimodal Model Acquisition
- Principle:Testtimescaling Testtimescaling github io Integration Verification
- Principle:AUTOMATIC1111 Stable diffusion webui Merge output options
- Principle:Huggingface Datasets Deterministic Serialization
- Principle:Mlc ai Web llm Extension Client Engine
- Principle:Ollama Ollama OpenAI Response Translation
Implementations
- Implementation:DistrictDataLabs Yellowbrick ClassPredictionError Visualizer
- Implementation:Trailofbits Fickling PyTorchModelWrapper Inject Payload
- Implementation:Axolotl ai cloud Axolotl Dynamic Dependencies
- Implementation:NVIDIA NeMo Aligner Train GPT KTO
- Implementation:Deepseek ai Janus Conversation Template
- Implementation:Datajuicer Data juicer VggtMapper
- Implementation:Ucbepic Docetl Directive DocCompression
- Implementation:LMCache LMCache Standalone Starter
- Implementation:Mage ai Mage ai Chargebee Plan Model Events Schema
- Implementation:Huggingface Datasets Languages Resource
Heuristics
- Heuristic:Microsoft DeepSpeedExamples SuperOffload NUMA Binding
- Heuristic:Facebookresearch Habitat lab Force Single Threaded PyTorch
- Heuristic:Vllm project Vllm GPU Memory Utilization Tuning
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:Puppeteer Puppeteer Firefox Single Process Workaround
- Heuristic:Puppeteer Puppeteer Chrome Default Launch Arguments
- Heuristic:Pola rs Polars GPU Aggregation Join Speedup
- Heuristic:Bigscience workshop Petals Prompt Embeddings Float32 Precision
- Heuristic:Allenai Open instruct Polyak Reference Update
- Heuristic:Duckdb Duckdb PR Submission Strategy
Environments
- Environment:Apache Kafka JVM Runtime Environment
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:Turboderp org Exllamav2 CUDA GPU Runtime
- Environment:Promptfoo Promptfoo Node Runtime
- Environment:Duckdb Duckdb Extension Distribution Env
- Environment:Microsoft Semantic kernel OpenAI API Environment
- Environment:Huggingface Datasets PyTorch Integration
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:Apache Spark JDK Build Environment