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:Togethercomputer Together python Batch Inference
- Workflow:Liu00222 Open Prompt Injection DataSentinel Detection
- Workflow:Helicone Helicone Local Development Setup
- Workflow:Interpretml Interpret Model Explanation And Visualization
- Workflow:Google deepmind Mujoco Model compilation and conversion
- Workflow:Apache Dolphinscheduler Workflow Execution Lifecycle
- Workflow:Apache Shardingsphere Metadata DDL Refresh
- Workflow:Huggingface Open r1 Model Evaluation
- Workflow:Mlc ai Mlc llm Mobile Deployment
- Workflow:NVIDIA TransformerEngine Accelerate HF Llama With TE
Principles
- Principle:LMCache LMCache RoPE Position Recovery
- Principle:ClickHouse ClickHouse Nfpm Package Generation
- Principle:FMInference FlexLLMGen Fused Transformer Layer CUDA
- Principle:Deepset ai Haystack Document Writing
- Principle:Heibaiying BigData Notes HBase Connection Creation
- Principle:Diagram of thought Diagram of thought Iterative Propose and Critique
- Principle:Apache Flink Async Sink Configuration
- Principle:FlagOpen FlagEmbedding Multi Retrieval Training
- Principle:ContextualAI HALOs Metrics Summarization
- Principle:Pytorch Serve Transformer Configuration
Implementations
- Implementation:Obss Sahi Download Mmdet Config
- Implementation:Ucbepic Docetl UseRestorePipeline
- Implementation:Scikit learn Scikit learn PlottingBase
- Implementation:Ggml org Llama cpp Chat Types
- Implementation:TobikoData Sqlmesh Graph Help
- Implementation:LMCache LMCache Mooncake Lookup Client
- Implementation:BerriAI Litellm Model Response
- Implementation:Langfuse Langfuse Dataset Run Items Repository
- Implementation:Recommenders team Recommenders Load Pandas Df
- Implementation:Togethercomputer Together python CodeInterpreter Run
Heuristics
- Heuristic:OpenGVLab InternVL Gradient Checkpointing Memory
- Heuristic:ARISE Initiative Robomimic Checkpoint Selection Strategy
- Heuristic:Microsoft Agent framework Tool Approval Mode Production
- Heuristic:Datahub project Datahub Gradle Task Only
- Heuristic:Huggingface Transformers Dataloader Pin Memory NonBlocking
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:Alibaba ROLL Dynamic Batching Token Limits
- Heuristic:Huggingface Datasets Warning Deprecated Pandas Builder
- Heuristic:Danijar Dreamerv3 Replay Context Carry Init
- Heuristic:Fastai Fastbook Progressive Resizing
Environments
- Environment:AnswerDotAI RAGatouille Python ColBERT Dependencies
- Environment:CrewAIInc CrewAI Optional Provider Dependencies
- Environment:OpenHands OpenHands Frontend Build Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Huggingface Open r1 Slurm Cluster
- Environment:Datahub project Datahub Docker Quickstart Environment
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:Open compass VLMEvalKit Python Runtime Environment
- Environment:Google deepmind Mujoco C Build Environment
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies