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:Cohere ai Cohere python AWS Bedrock Deployment
- Workflow:ArroyoSystems Arroyo SQL Pipeline Lifecycle
- Workflow:Dagster io Dagster Dbt Integration
- Workflow:Openclaw Openclaw Multi Agent Routing
- Workflow:Vllm project Vllm Offline Text Generation
- Workflow:Openai Openai python Embeddings Generation
- Workflow:Protectai Modelscan Programmatic Model Scanning
- Workflow:Tensorflow Tfjs Pretrained Model Conversion And Inference
- Workflow:Axolotl ai cloud Axolotl QLoRA SFT Finetuning
- Workflow:Interpretml Interpret Model Explanation And Visualization
Principles
- Principle:Google deepmind Mujoco Constraint Solver
- Principle:Truera Trulens Snowflake Connection Configuration
- Principle:Allenai Open instruct DPO Loss
- Principle:Testtimescaling Testtimescaling github io Badge Data Generation
- Principle:Predibase Lorax Stateless Conversation Management
- Principle:LMCache LMCache Prefill Decode Configuration
- Principle:Bitsandbytes foundation Bitsandbytes FP8 Linear Layer
- Principle:Infiniflow Ragflow File Management
- Principle:Mlc ai Mlc llm Model Packaging Configuration
- Principle:AUTOMATIC1111 Stable diffusion webui Prompt Syntax
Implementations
- Implementation:Microsoft DeepSpeedExamples BingBert DeepSpeedTrain
- Implementation:Pola rs Polars Group By Dynamic
- Implementation:Infiniflow Ragflow UserCanvasService Save
- Implementation:LLMBook zh LLMBook zh github io Apply Rotary Pos Emb
- Implementation:Microsoft Semantic kernel CloudEvents App
- Implementation:Open compass VLMEvalKit ScreenSpot
- Implementation:Microsoft Autogen Studio Chat Input
- Implementation:Kornia Kornia Hsv Conversion
- Implementation:Haotian liu LLaVA Load Pretrained Model
- Implementation:FlowiseAI Flowise CredentialInputHandler
Heuristics
- Heuristic:Sgl project Sglang Schedule Conservativeness Tuning
- Heuristic:Datahub project Datahub Gradle Formatting Over Direct Tools
- Heuristic:Openai Whisper SDPA Disabling For Attention Extraction
- Heuristic:SeleniumHQ Selenium Cross Binding Consistency Check
- Heuristic:Risingwavelabs Risingwave Memory Cache Eviction Policy
- Heuristic:Norrrrrrr lyn WAInjectBench LoRA Rank Alpha Selection
- Heuristic:Pyro ppl Pyro Numerical Stability Patterns
- Heuristic:Liu00222 Open Prompt Injection PPL Threshold Tuning
- Heuristic:Facebookresearch Habitat lab DDPPO Straggler Preemption
- Heuristic:Huggingface Datasets Cache Fingerprinting Tips
Environments
- Environment:Alibaba ROLL SGLang Inference Environment
- Environment:SeldonIO Seldon core Kubernetes Cluster Environment
- Environment:Vllm project Vllm Buildkite
- Environment:Datahub project Datahub Python Ingestion
- Environment:Microsoft BIPIA OpenAI API Environment
- Environment:Spcl Graph of thoughts Python 3 8 Runtime
- Environment:Kornia Kornia ONNX Runtime Environment
- Environment:Confident ai Deepeval Python 3 9 Runtime
- Environment:Sgl project Sglang CPU Runtime
- Environment:Huggingface Datasets Python PyArrow Core