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:Bitsandbytes foundation Bitsandbytes 8bit LLM Int8 Inference
- Workflow:Dotnet Machinelearning AutoML Experiment
- Workflow:Spcl Graph of thoughts GoT Document Merging Pipeline
- Workflow:Microsoft Onnxruntime On Device Training
- Workflow:Huggingface Diffusers DreamBooth Personalization
- Workflow:Huggingface Diffusers Text to Image Inference
- Workflow:Huggingface Alignment handbook ORPO Single Stage Alignment
- Workflow:TobikoData Sqlmesh Github CICD automation
- Workflow:Vllm project Vllm Speculative Decoding
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
Principles
- Principle:Turboderp org Exllamav2 Layer Quantization
- Principle:ARISE Initiative Robosuite Texture Randomization
- Principle:Neuml Txtai Multi Vector Encoding
- Principle:Pyro ppl Pyro Probabilistic Modeling
- Principle:Tencent Ncnn Layer Abstraction
- Principle:Farama Foundation Gymnasium Q Learning Tabular
- Principle:Unstructured IO Unstructured Basic Chunking
- Principle:Ray project Ray Deployment Configuration And Binding
- Principle:Apache Airflow Community Voting
- Principle:Heibaiying BigData Notes Hive Partitioning and Bucketing
Implementations
- Implementation:Huggingface Datatrove StatsMerger
- Implementation:Open compass VLMEvalKit MMHelix Tapa Eval
- Implementation:Ggml org Llama cpp Jinja Value
- Implementation:Ggml org Ggml Sycl dmmv
- Implementation:Hpcaitech ColossalAI Eval Conversation
- Implementation:Arize ai Phoenix Legacy Audio Templates
- Implementation:FlowiseAI Flowise SafeHTML
- Implementation:Datajuicer Data juicer EntityAttributeAggregator
- Implementation:Scikit learn Scikit learn SAG Solver
- Implementation:MarketSquare Robotframework browser Settings Stack
Heuristics
- Heuristic:Triton inference server Server Model Instance Scaling
- Heuristic:Liu00222 Open Prompt Injection Attack Effectiveness Hierarchy
- Heuristic:Evidentlyai Evidently Column Type Inference Rules
- Heuristic:Pytorch Serve CPU Performance Tuning
- Heuristic:Fede1024 Rust rdkafka Regular Polling Required
- Heuristic:Vllm project Vllm Attention Backend Selection
- Heuristic:Arize ai Phoenix Warning Deprecated HallucinationEvaluator
- Heuristic:Apache Dolphinscheduler HikariCP Pool Tuning
- Heuristic:Tensorflow Tfjs GPU Pipeline Data Residency
- Heuristic:Iamhankai Forest of Thought UCB Exploration Constant
Environments
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Cohere ai Cohere python AWS Integration Dependencies
- Environment:Openai Evals Python Runtime
- Environment:Cohere ai Cohere python Python SDK Runtime
- Environment:Hpcaitech ColossalAI GRPO Distributed Environment
- Environment:Sgl project Sglang Prometheus
- Environment:Mit han lab Llm awq Python Runtime Environment
- Environment:Kserve Kserve Cert Manager
- Environment:Dotnet Machinelearning Platform Architecture Support
- Environment:Farama Foundation Gymnasium Box2D Physics Backend