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:Unslothai Unsloth QLoRA SFT Finetuning
- Workflow:Microsoft Agent framework Agent With Tool Approval
- Workflow:Treeverse LakeFS External Data Import
- Workflow:Cypress io Cypress CI Pipeline Integration
- Workflow:Diagram of thought Diagram of thought DoT Trace Extraction
- Workflow:Kserve Kserve Multi Model Serving
- Workflow:Ggml org Ggml Vision Model Inference
- Workflow:Apache Druid SQL Query Execution
- Workflow:Protectai Modelscan Custom Scanner Plugin
- Workflow:Truera Trulens Snowflake Observability Pipeline
Principles
- Principle:Fastai Fastbook Feature Importance
- Principle:Tencent Ncnn Vulkan Pipeline Optimization
- Principle:Pyro ppl Pyro MCMC Posterior Prediction
- Principle:Langgenius Dify EventDrivenCommunication
- Principle:Neuml Txtai ANN Backend Architecture
- Principle:Apache Druid Tuning Parameters
- Principle:Sdv dev SDV Sequential Model Fitting
- Principle:TA Lib Ta lib python Cython Binding Generation
- Principle:Mit han lab Llm awq VLM Benchmarking
- Principle:Nautechsystems Nautilus trader Config Driven Backtesting
Implementations
- Implementation:Microsoft Autogen Studio Auth Middleware
- Implementation:Infiniflow Ragflow FloatingChatWidgetMarkdown Component
- Implementation:BerriAI Litellm Aporia AI Guardrail
- Implementation:Hpcaitech ColossalAI Zero Bubble Producer
- Implementation:EvolvingLMMs Lab Lmms eval IFEval Instructions Registry
- Implementation:Vllm project Vllm Torch Bindings
- Implementation:Langchain ai Langchain ExaSearchTools
- Implementation:Scikit learn Scikit learn LinkFunctions
- Implementation:FlagOpen FlagEmbedding LLM Dense Retriever Data
- Implementation:ArroyoSystems Arroyo Start Pipeline Modal
Heuristics
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:LLMBook zh LLMBook zh github io Reward Model LM Regularization
- Heuristic:Openai Evals Chat Format Recommendation
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Allenai Open instruct Logprob Clamping
- Heuristic:Avdvg InjectGuard Module Level Initialization
- Heuristic:Unstructured IO Unstructured PDF Element Sorting
- Heuristic:FlowiseAI Flowise Edge Connection Type Matching
- Heuristic:Heibaiying BigData Notes HBase Connection Thread Safety Tip
- Heuristic:Deepspeedai DeepSpeed Vocabulary Tensor Core Alignment
Environments
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Protectai Llm guard API Server Deployment
- Environment:Huggingface Datasets Audio Video Dependencies
- Environment:Cypress io Cypress Browser Requirements
- Environment:Google deepmind Dm control Python MuJoCo Runtime
- Environment:Kubeflow Pipelines Kubernetes Cluster
- Environment:Vllm project Vllm Distributed
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Axolotl ai cloud Axolotl CUDA GPU
- Environment:Langchain ai Langgraph Docker Deployment Environment