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:Intel Ipex llm QLoRA Finetuning
- Workflow:Haotian liu LLaVA Web Demo Deployment
- Workflow:Danijar Dreamerv3 Evaluation Only
- Workflow:CrewAIInc CrewAI Sequential Crew Execution
- Workflow:SeleniumHQ Selenium Selenium Grid Deployment
- Workflow:Nautechsystems Nautilus trader Backtest with BacktestNode
- Workflow:Lucidrains X transformers DPO Preference Alignment
- Workflow:Microsoft Agent framework Graph Based Workflow Execution
- Workflow:Alibaba MNN Python Model Inference
- Workflow:Avdvg InjectGuard Vector Similarity Detection Pipeline
Principles
- Principle:AnswerDotAI RAGatouille Semantic Search
- Principle:Apache Paimon Blob Schema Definition
- Principle:Bitsandbytes foundation Bitsandbytes Columnwise INT8 Quantization
- Principle:Huggingface Optimum Quantized Weight Packing
- Principle:Ollama Ollama Model Loading
- Principle:Ray project Ray Request Routing And Handling
- Principle:Mlc ai Web llm Cross Thread Streaming
- Principle:LMCache LMCache RoPE Position Recovery
- Principle:PeterL1n BackgroundMattingV2 Homographic alignment
- Principle:Apache Paimon Developer Tooling
Implementations
- Implementation:Huggingface Peft CartridgeConfig
- Implementation:Speechbrain Speechbrain Prepare Voicebank MTL
- Implementation:Langgenius Dify CLI Commands
- Implementation:FlagOpen FlagEmbedding AbsEvalArgs Configuration
- Implementation:Ggml org Llama cpp LoRA Download
- Implementation:Isaac sim IsaacGymEnvs CommonAgent Train
- Implementation:Evidentlyai Evidently Guardrails Trace
- Implementation:Haosulab ManiSkill BaseMotionPlanningSolver
- Implementation:Recommenders team Recommenders A2SVD Model
- Implementation:EvolvingLMMs Lab Lmms eval Cache Utils
Heuristics
- Heuristic:Protectai Modelscan Exit Code Conventions
- Heuristic:Tensorflow Tfjs Memory Management With Tidy
- Heuristic:Eric mitchell Direct preference optimization TF32 Matmul Precision
- Heuristic:Open compass VLMEvalKit API Retry With Random Delay
- Heuristic:Lakeraai Pint benchmark Chunking Stride 25 Percent Overlap
- Heuristic:Intel Ipex llm Llama Padding Token Workaround
- Heuristic:Speechbrain Speechbrain Score Normalization Tips
- Heuristic:PrefectHQ Prefect Retry Backoff Strategy
- Heuristic:ContextualAI HALOs FSDP Sampling Workaround
- Heuristic:Tencent Ncnn NMS Threshold Tuning
Environments
- Environment:Wandb Weave Python SDK Runtime
- Environment:Kserve Kserve SRIOV RDMA Network
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Tensorflow Tfjs Node Native Runtime
- Environment:Unstructured IO Unstructured GitHub Actions
- Environment:Vllm project Vllm GitHub
- Environment:Huggingface Diffusers Attention Backends
- Environment:Webdriverio Webdriverio Node Runtime Environment
- Environment:Getgauge Taiko Docker Container
- Environment:Langchain ai Langchain Python 3 10 Runtime