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
__NOCACHE__
Workflows
- Workflow:Huggingface Open r1 Model Evaluation
- Workflow:Groq Groq python Chat Completion
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:Deepspeedai DeepSpeed Inference Engine Optimization
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Translation
- Workflow:Cleanlab Cleanlab Classification Label Issue Detection
- Workflow:Openai Openai node Fine Tuning
- Workflow:Nautechsystems Nautilus trader Live trading deployment
- Workflow:Confident ai Deepeval Component Level LLM Evaluation
Principles
- Principle:LLMBook zh LLMBook zh github io Rotary Position Embedding
- Principle:Ggml org Llama cpp HTTP Utilities
- Principle:Huggingface Optimum Preprocessor Persistence
- Principle:Ucbepic Docetl Output Management
- Principle:Sail sg LongSpec VLLM Inference Client
- Principle:Arize ai Phoenix Batch Span Annotation
- Principle:FlowiseAI Flowise Lead Capture
- Principle:Farama Foundation Gymnasium Action Transformation
- Principle:Online ml River Bandit Datasets
- Principle:DistrictDataLabs Yellowbrick Influential Outlier Detection
Implementations
- Implementation:OpenHands OpenHands SaasNestedConversationManager Refresh Tokens
- Implementation:CrewAIInc CrewAI Merge Agent Handler Tool
- Implementation:Apache Druid TasksCard
- Implementation:Togethercomputer Together python Embeddings Create
- Implementation:Huggingface Datatrove LanguageIdentifier
- Implementation:Ollama Ollama MLXRunner Slice
- Implementation:Explodinggradients Ragas ImageTextPrompt Class
- Implementation:Tensorflow Tfjs EinsumDense Test
- Implementation:LaurentMazare Tch rs Seq2Seq Translation
- Implementation:Facebookresearch Audiocraft MultiScaleDiscriminator
Heuristics
- Heuristic:Mlc ai Mlc llm OpenCL Memory Floor Workaround
- Heuristic:Openclaw Openclaw Conservative Error Retry Classification
- Heuristic:Explodinggradients Ragas Deprecation Migration Guide
- Heuristic:Kornia Kornia Avoid Inplace Ops Compile
- Heuristic:Lance format Lance Encoding Compression Thresholds
- Heuristic:FMInference FlexLLMGen OOM Memory Management
- Heuristic:Langfuse Langfuse BullMQ Retry Strategy Patterns
- Heuristic:CARLA simulator Carla Traffic Manager Sync Mode
- Heuristic:FlowiseAI Flowise Tool Ordering Convention
- Heuristic:Openai Openai agents python Default Max Turns Safety Limit
Environments
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:Shiyu coder Kronos PyTorch CUDA Environment
- Environment:Eric mitchell Direct preference optimization HuggingFace Transformers
- Environment:OpenRLHF OpenRLHF DeepSpeed Environment
- Environment:Apache Spark Kubernetes Runtime
- Environment:Nightwatchjs Nightwatch BrowserStack Cloud
- Environment:DataTalksClub Data engineering zoomcamp Dlt BigQuery Environment
- Environment:Vllm project Vllm Buildkite
- Environment:OpenGVLab InternVL Flash Attention 2
- Environment:Vllm project Vllm CUDA