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:Allenai Open instruct GRPO Reinforcement Learning
- Workflow:CarperAI Trlx ILQL Offline Training
- Workflow:MarketSquare Robotframework browser Browser Test Authoring
- Workflow:Mit han lab Llm awq TinyChat LLM Deployment
- Workflow:Huggingface Datasets Dataset Streaming
- Workflow:PacktPublishing LLM Engineers Handbook LLM Finetuning
- Workflow:Microsoft Semantic kernel Agent Conversation And Orchestration
- Workflow:Protectai Llm guard LLM Input Output Scanning
- Workflow:Mbzuai oryx Awesome LLM Post training Deep Paper Collection
- Workflow:Microsoft Autogen Swarm Agent Handoff
Principles
- Principle:Zai org CogVideo VAE Encode Decode
- Principle:Romsto Speculative Decoding Encoder Decoder Autoregressive Generation
- Principle:Mit han lab Llm awq Pseudo Quantization
- Principle:Microsoft Onnxruntime Nodejs Session Creation
- Principle:Nautechsystems Nautilus trader External Data Loading
- Principle:Nautechsystems Nautilus trader Instrument Specification
- Principle:Farama Foundation Gymnasium Functional Environment API
- Principle:Marker Inc Korea AutoRAG Export And Corpus Remapping
- Principle:Guardrails ai Guardrails DataGeneration
- Principle:Scikit learn Scikit learn Robust Regression
Implementations
- Implementation:Ucbepic Docetl ExperimentStructuredOutputs
- Implementation:Intel Ipex llm GaLore Finetuning
- Implementation:Kornia Kornia Welsch Loss
- Implementation:CrewAIInc CrewAI Parallel Search Tool
- Implementation:Bentoml BentoML Cloud ModelAPI
- Implementation:Ollama Ollama Mtmd CogVLM
- Implementation:Triton inference server Server L0 Backend Config Test
- Implementation:Microsoft Autogen Swarm Init
- Implementation:Vllm project Vllm CPU Torch Bindings
- Implementation:Ggml org Ggml Sycl dequantize
Heuristics
- Heuristic:Vibrantlabsai Ragas Analytics Silent Failure Pattern
- Heuristic:Scikit learn Scikit learn Convergence Warning Handling
- Heuristic:Huggingface Datasets Shuffle Buffer Sizing
- Heuristic:Tensorflow Serving Servable Handle Lifetime
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Openai Whisper Log Probability Threshold
- Heuristic:Liu00222 Open Prompt Injection PPL Threshold Tuning
- Heuristic:Mit han lab Llm awq Kernel Selection Thresholds
- Heuristic:Teamcapybara Capybara Frozen Time Detection
Environments
- Environment:Langfuse Langfuse S3 Compatible Storage
- Environment:ClickHouse ClickHouse CI Docker Environment
- Environment:Alibaba ROLL SGLang Inference Environment
- Environment:Shiyu coder Kronos Qlib Data Environment
- Environment:Open compass VLMEvalKit Data Storage Environment
- Environment:Kornia Kornia ONNX Runtime Environment
- Environment:VainF Torch Pruning PyTorch Python Core
- Environment:Vllm project Vllm Python Dependencies
- Environment:Kserve Kserve Python Runtime
- Environment:Huggingface Peft Optional Quantization Backends