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:Langfuse Langfuse Evaluation pipeline
- Workflow:Pola rs Polars Time Series Analysis
- Workflow:DevExpress Testcafe CI Integration
- Workflow:Langchain ai Langgraph Building a Stateful Graph
- Workflow:Mage ai Mage ai Building a New Destination Connector
- Workflow:SeldonIO Seldon core Production Monitoring Pipeline
- Workflow:Openai Evals Running a single eval
- Workflow:Princeton nlp Tree of thought llm Baseline comparison
- Workflow:Langchain ai Langgraph Functional API Workflow
- Workflow:Rapidsai Cuml Dimensionality Reduction
Principles
- Principle:Tensorflow Tfjs Recurrent Neural Networks
- Principle:Getgauge Taiko Input Clearing
- Principle:Facebookresearch Habitat lab Agent Implementation
- Principle:Treeverse LakeFS Import Tagging
- Principle:Infiniflow Ragflow LLM Configuration
- Principle:Avhz RustQuant Mathematical Sequences
- Principle:Infiniflow Ragflow LLM Provider Initialization
- Principle:Pola rs Polars Query Plan Inspection
- Principle:Pytorch Serve Multimodal Inference
- Principle:Langgenius Dify Processing Node Configuration
Implementations
- Implementation:Intel Ipex llm AutoModelForCausalLM From Pretrained QLoRA
- Implementation:Ggml org Llama cpp Llama Decode
- Implementation:Huggingface Datasets Generator Builder
- Implementation:Deepspeedai DeepSpeed LinearAllreduce Forward
- Implementation:NVIDIA NeMo Curator NSFWScorer
- Implementation:Farama Foundation Gymnasium Gymnasium Make
- Implementation:Microsoft DeepSpeedExamples Nvidia Bert Dataset Provider
- Implementation:Alibaba MNN Protobuf Wrappers PB H
- Implementation:Langfuse Langfuse CreateEvalQueue
- Implementation:InternLM Lmdeploy Gemm KernelImplSm90
Heuristics
- Heuristic:Mlc ai Mlc llm FlashInfer KV Cache Fallback
- Heuristic:Tensorflow Serving Model Warmup Strategy
- Heuristic:LaurentMazare Tch rs Hidden Dimension Alignment
- Heuristic:Openclaw Openclaw WebSocket Reconnection And Session Cleanup
- Heuristic:Tensorflow Tfjs GPU Pipeline Data Residency
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:Triton inference server Server Model Instance Scaling
- Heuristic:TA Lib Ta lib python Thread Safety With Abstract API
- Heuristic:SqueezeAILab ETS Lambda Similarity Scaling
- Heuristic:PeterL1n BackgroundMattingV2 Data Augmentation Strategy
Environments
- Environment:TobikoData Sqlmesh Python Runtime
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:OpenGVLab InternVL PyTorch CUDA
- Environment:Openai CLIP PyTorch CUDA Runtime
- Environment:Openai Openai agents python MCP Dependencies
- Environment:CrewAIInc CrewAI Python Runtime Environment
- Environment:Ggml org Llama cpp Metal GPU Environment
- Environment:Turboderp org Exllamav2 CUDA GPU Runtime
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:Axolotl ai cloud Axolotl Python Runtime