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:OWASP Www project top 10 for large language model applications Vulnerability Translation
- Workflow:Langfuse Langfuse Otel ingestion pipeline
- Workflow:Google research Deduplicate text datasets Single file deduplication
- Workflow:Deepseek ai Janus Rectified Flow Image Generation
- Workflow:Deepseek ai Janus Autoregressive Image Generation
- Workflow:CARLA simulator Carla Traffic Generation
- Workflow:Heibaiying BigData Notes HBase Java CRUD Operations
- Workflow:Langgenius Dify Application Creation
- Workflow:CarperAI Trlx SFT Instruction Tuning
- Workflow:Alibaba MNN Model Compression
Principles
- Principle:AUTOMATIC1111 Stable diffusion webui Launch Sequence
- Principle:Haotian liu LLaVA Model Worker Inference
- Principle:Confident ai Deepeval Batch Evaluation Execution
- Principle:Microsoft Autogen Team Execution
- Principle:Tencent Ncnn Vulkan GPU Detection
- Principle:Cleanlab Cleanlab Datalab Regression Label Issue Detection
- Principle:Anthropics Anthropic sdk python Provider Client Initialization
- Principle:Apache Flink Element Conversion
- Principle:Getgauge Taiko Request Redirect
- Principle:Cleanlab Cleanlab Class Level Quality Ranking
Implementations
- Implementation:Evidentlyai Evidently Legacy Color Options
- Implementation:PacktPublishing LLM Engineers Handbook CleaningDispatcher Dispatch
- Implementation:ARISE Initiative Robosuite Observables
- Implementation:Isaac sim IsaacGymEnvs DR Utils Random Samples
- Implementation:Microsoft LoRA Check TF Ops
- Implementation:TobikoData Sqlmesh UseColumnLevelLineage
- Implementation:NVIDIA TransformerEngine TEGemmaDecoderLayer
- Implementation:Vllm project Vllm EngineArgs Init
- Implementation:Avhz RustQuant OptionContract
- Implementation:Tencent Ncnn Extractor Vulkan Compute
Heuristics
- Heuristic:Huggingface Optimum Device Offload Constraints
- Heuristic:Zai org CogVideo Frame Count and Resolution Constraints
- Heuristic:ContextualAI HALOs Reference Logprob Caching
- Heuristic:Anthropics Anthropic sdk python Adaptive Thinking Over Enabled
- Heuristic:Sktime Pytorch forecasting Target Normalization Transforms
- Heuristic:SeldonIO Seldon core Tracing Latency Tip
- Heuristic:Farama Foundation Gymnasium Action Space Normalization Tip
- Heuristic:Huggingface Peft RSLoRA Scaling
- Heuristic:Deepspeedai DeepSpeed FP16 Convergence Tips
- Heuristic:Explodinggradients Ragas Concurrency And Rate Limiting
Environments
- Environment:Nightwatchjs Nightwatch Selenium WebDriver 4
- Environment:Recommenders team Recommenders Python Core Dependencies
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:Huggingface Transformers Flash Attention 2 Env
- Environment:Mlc ai Mlc llm Metal macOS iOS Environment
- Environment:NVIDIA DALI CUDA GPU Environment
- Environment:Facebookresearch Audiocraft Python PyTorch CUDA Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:Huggingface Peft Optional Quantization Backends
- Environment:Huggingface Alignment handbook PyTorch CUDA