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:Neuml Txtai RAG Pipeline
- Workflow:Alibaba ROLL DPO Training Pipeline
- Workflow:Huggingface Datatrove Dataset Tokenization
- Workflow:PacktPublishing LLM Engineers Handbook Digital Data ETL
- Workflow:Langchain ai Langchain Release Process
- Workflow:Mlc ai Mlc llm REST API Serving
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
- Workflow:Astronomer Astronomer cosmos Local dbt DAG rendering
- Workflow:Neuml Txtai Semantic Search
- Workflow:Openai Evals Running an eval set
Principles
- Principle:Ggml org Ggml Tensor Context Management
- Principle:Huggingface Datatrove Document Filtering Framework
- Principle:Arize ai Phoenix Client Initialization
- Principle:AUTOMATIC1111 Stable diffusion webui Hypernetwork architecture
- Principle:Treeverse LakeFS Java SDK API Operations
- Principle:MaterializeInc Materialize Release Prerequisite Verification
- Principle:Microsoft Autogen Team Deployment
- Principle:Triton inference server Server Dynamic Batching Testing
- Principle:OWASP Www project top 10 for large language model applications Mitigation Gap Analysis
- Principle:OpenBMB UltraFeedback Model Loading
Implementations
- Implementation:Lance format Lance JNI BlockingDataset
- Implementation:Lance format Lance Commit Compaction
- Implementation:Microsoft Playwright Public Protocol Types
- Implementation:OWASP Www project top 10 for large language model applications FeedbackGenerator Generate
- Implementation:Ggml org Ggml Cpu vec ops
- Implementation:Facebookresearch Habitat lab AppStateTutorial
- Implementation:Ggml org Llama cpp Grammar Header
- Implementation:Open compass VLMEvalKit BMMR Grade
- Implementation:Helicone Helicone GetUsageProcessor
- Implementation:Infiniflow Ragflow TestingResult Component
Heuristics
- Heuristic:Truera Trulens Rate Limiting And Retry Strategy
- Heuristic:HKUDS AI Trader Linear Retry Backoff
- Heuristic:Snorkel team Snorkel Binary Only Slicing
- Heuristic:LLMBook zh LLMBook zh github io Reward Model LM Regularization
- Heuristic:Unslothai Unsloth Gradient Accumulation Accuracy
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:PacktPublishing LLM Engineers Handbook Token Window Safety Margin
- Heuristic:Zai org CogVideo DeepSpeed Checkpoint Conversion Tips
- Heuristic:MarketSquare Robotframework browser MacOS Sonoma Startup Delay
- Heuristic:Bigscience workshop Petals Randomized Rebalancing Intervals
Environments
- Environment:Langchain ai Langchain Anthropic API Credentials
- Environment:OpenBMB UltraFeedback vLLM Multi GPU Environment
- Environment:Elevenlabs Elevenlabs python Python Httpx
- Environment:Haosulab ManiSkill Motion Planning Deps
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Huggingface Datatrove S3 Storage Environment
- Environment:Ggml org Ggml Metal GPU Environment
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas
- Environment:Datahub project Datahub Docker Runtime