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:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Puppeteer Puppeteer Page Screenshot Capture
- Workflow:Explodinggradients Ragas Prompt Evaluation And Iteration
- Workflow:Apache Hudi Flink Streaming Write
- Workflow:Iterative Dvc Plot Visualization
- Workflow:Huggingface Datasets Dataset Streaming
- Workflow:Tensorflow Serving Model Export And Serving
- Workflow:AUTOMATIC1111 Stable diffusion webui Hypernetwork training
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Heibaiying BigData Notes Storm Topology Development
Principles
- Principle:PacktPublishing LLM Engineers Handbook AWS IAM Role Provisioning
- Principle:FlowiseAI Flowise Document Processing
- Principle:Pyro ppl Pyro No U Turn Sampling
- Principle:Tensorflow Serving HTTP Server Implementation
- Principle:Volcengine Verl Reward Model Scoring
- Principle:Elevenlabs Elevenlabs python Text to Speech Conversion
- Principle:Apache Beam Transform Override Application Twister2
- Principle:Apache Spark Release Environment Isolation
- Principle:Huggingface Open r1 Environment Setup
- Principle:Langgenius Dify Single Node Testing
Implementations
- Implementation:Ollama Ollama Llama Model GLM4
- Implementation:Apache Shardingsphere ShowProcessListHandler Handle
- Implementation:Eventual Inc Daft DataFrame Explain
- Implementation:Duckdb Duckdb LZ4 Compression
- Implementation:CARLA simulator Carla ObjectLabel
- Implementation:Ggml org Ggml Cpp smart pointers
- Implementation:Treeverse LakeFS Java SDK RepositoriesApi
- Implementation:Huggingface Datasets Get Dataset Config Info
- Implementation:Kubeflow Pipelines Compiler Compile
- Implementation:Explodinggradients Ragas BasePrompt Class
Heuristics
- Heuristic:Groq Groq python Timeout Configuration
- Heuristic:Zai org CogVideo Training Hyperparameter Defaults
- Heuristic:Microsoft Autogen Warning Deprecated JSON Env Files
- Heuristic:Alibaba MNN LLM Runtime Tuning
- Heuristic:Langchain ai Langchain Retry Scope Best Practice
- Heuristic:FlagOpen FlagEmbedding Temperature Scaling Tip
- Heuristic:OpenRLHF OpenRLHF Off Policy IS Correction Tip
- Heuristic:Speechbrain Speechbrain Dynamic Mixing Parameters
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
- Heuristic:Zai org CogVideo Decord Import Order Bug
Environments
- Environment:InternLM Lmdeploy CUDA GPU Runtime
- Environment:Togethercomputer Together python API Credentials
- Environment:Tencent Ncnn Build Environment
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:Datahub project Datahub Docker Runtime
- Environment:Apache Druid Web Console Development
- Environment:Interpretml Interpret Native Libebm Environment
- Environment:Ggml org Ggml Python Tooling Environment
- Environment:Zai org CogVideo Video Captioning Environment
- Environment:Alibaba ROLL DeepSpeed Training Environment