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:DevExpress Testcafe Basic Test Authoring
- Workflow:PrefectHQ Prefect Database Cleanup With Approval
- Workflow:Pytorch Serve HuggingFace Transformer Serving
- Workflow:Google deepmind Dm control Locomotion Task Setup
- Workflow:DataExpert io Data engineer handbook Flink Kafka Streaming Pipeline
- Workflow:Testtimescaling Testtimescaling github io Adding a New Paper
- Workflow:Openai Evals Running an eval set
- Workflow:Anthropics Anthropic sdk python Streaming Message Interaction
- Workflow:Vibrantlabsai Ragas Experiment Driven Development
Principles
- Principle:Hpcaitech ColossalAI Document Loading
- Principle:Huggingface Datatrove Media Writing Framework
- Principle:Ollama Ollama Model Manifest Creation
- Principle:ClickHouse ClickHouse Program Component Compilation
- Principle:Pyro ppl Pyro SVI Training Loop
- Principle:Lm sys FastChat OpenAI Compatible API Serving
- Principle:FlowiseAI Flowise Application Configuration
- Principle:Eventual Inc Daft Table Writing
- Principle:Ggml org Llama cpp KVCacheManagement
- Principle:Alibaba ROLL Teacher Forward Inference
Implementations
- Implementation:Farama Foundation Gymnasium Play
- Implementation:Marker Inc Korea AutoRAG Dontknow Filter Rule Based
- Implementation:Microsoft Onnxruntime Generate Artifacts
- Implementation:Cohere ai Cohere python NonStreamedChatResponse Model
- Implementation:NVIDIA DALI Paddle ResNet Training
- Implementation:Ollama Ollama Convert Qwen3
- Implementation:Run llama Llama index LLMQuestionGenerator
- Implementation:Diagram of thought Diagram of thought Node Edge Status Regex Extraction
- Implementation:Zai org CogVideo CogVLM2 Predict
- Implementation:Helicone Helicone UseUpgradePlan
Heuristics
- Heuristic:Google deepmind Dm control Tolerance Reward Tuning
- Heuristic:Predibase Lorax Quantization Backend Selection
- Heuristic:Mlc ai Web llm Service Worker Keep Alive
- Heuristic:Openai Whisper Log Probability Threshold
- Heuristic:Vespa engine Vespa Document Batch Processing Strategy
- Heuristic:PeterL1n BackgroundMattingV2 Training Batch Size And Resolution
- Heuristic:Mbzuai oryx Awesome LLM Post training Reference Citation Cap 200
- Heuristic:Avhz RustQuant Interpolation Method Selection
- Heuristic:Pyro ppl Pyro Gradient Variance Reduction
- Heuristic:Sgl project Sglang Schedule Conservativeness Tuning
Environments
- Environment:Alibaba MNN HuggingFace Ecosystem Environment
- Environment:Promptfoo Promptfoo Python Runtime
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:Alibaba ROLL DeepSpeed Training Environment
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:Intel Ipex llm Build Environment
- Environment:PacktPublishing LLM Engineers Handbook Unsloth Finetuning Environment
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Arize ai Phoenix OpenTelemetry SDK