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, 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:Bentoml BentoML Multi Model Composition
- Workflow:Arize ai Phoenix LLM Evaluation Pipeline
- Workflow:DevExpress Testcafe Basic Test Authoring
- Workflow:Zai org CogVideo Video Editing DDIM Inversion
- Workflow:Langchain ai Langchain Vector Store Operations
- Workflow:Roboflow Rf detr Object Detection Inference
- Workflow:Farama Foundation Gymnasium Policy Gradient Training
- Workflow:Kubeflow Kubeflow Contributing To Kubeflow
- Workflow:Helicone Helicone Local Development Setup
- Workflow:Apache Hudi Flink Schema Evolution
Principles
- Principle:AUTOMATIC1111 Stable diffusion webui Progress Reporting
- Principle:Huggingface Transformers Model Loading For Training
- Principle:Cleanlab Cleanlab Active Learning Prioritization
- Principle:OWASP Www project top 10 for large language model applications Automated Quality Feedback
- Principle:Apache Kafka Coordinator State Loading
- Principle:ARISE Initiative Robosuite Object Modeling
- Principle:Heibaiying BigData Notes MapReduce Job Assembly
- Principle:Truera Trulens Output Blocking Guardrail
- Principle:Pola rs Polars Temporal Data Parsing
- Principle:MarketSquare Robotframework browser Installation Path Selection
Implementations
- Implementation:Openai Whisper Median Filter
- Implementation:Kornia Kornia Lovasz Hinge Loss
- Implementation:TobikoData Sqlmesh Load Sql Based Model
- Implementation:LaurentMazare Tch rs Tensor Generated
- Implementation:Tensorflow Tfjs Metrics Test
- Implementation:Duckdb Duckdb Release Upload Scripts
- Implementation:Kornia Kornia Mean IoU
- Implementation:SeleniumHQ Selenium Closure UI MenuButton
- Implementation:FlowiseAI Flowise DefaultRedirect
- Implementation:TA Lib Ta lib python Stream Wrapper Integration
Heuristics
- Heuristic:Deepset ai Haystack Pipeline Deep Copy Safety
- Heuristic:Snorkel team Snorkel Precision Init Prior
- Heuristic:Sail sg LongSpec Triton Block Size Tuning
- Heuristic:NVIDIA TransformerEngine FP8 Recipe Auto Selection
- Heuristic:Huggingface Peft DoRA Inference Caching
- Heuristic:FlagOpen FlagEmbedding Same Dataset Batching Tip
- Heuristic:Bigscience workshop Petals Batch Splitting Threshold
- Heuristic:Microsoft Autogen Agent Thread Safety
- Heuristic:Turboderp org Exllamav2 Memory Optimization Techniques
- Heuristic:Hiyouga LLaMA Factory Gradient Checkpointing Memory Optimization
Environments
- Environment:OpenBMB UltraFeedback Python GPU Environment
- Environment:Triton inference server Server GPU CUDA Runtime
- Environment:Openai CLIP Python Dependencies
- Environment:Evidentlyai Evidently LLM Evaluation Environment
- Environment:Huggingface Datatrove IO Dependencies
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:Tencent Ncnn PyTorch Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas
- Environment:Ggml org Ggml Vulkan GPU Environment
- Environment:Huggingface Optimum Accelerated Inference Environment