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:Groq Groq python Streaming Chat Completion
- Workflow:Scikit learn Scikit learn Hyperparameter Tuning
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:FMInference FlexLLMGen Single GPU Offloaded Inference
- Workflow:Zai org CogVideo Diffusers Image to Video Inference
- Workflow:Treeverse LakeFS Data Version Control With Branches
- Workflow:Haosulab ManiSkill RL Training with PPO
- Workflow:Triton inference server Server Model Performance Tuning
- Workflow:Groq Groq python Text Embedding
- Workflow:Truera Trulens LangGraph Agent Evaluation
Principles
- Principle:Webdriverio Webdriverio Selector Optimization
- Principle:Apache Shardingsphere Configuration Change Initiation
- Principle:Microsoft DeepSpeedExamples Multi Dataset VQA Preparation
- Principle:Mlfoundations Open flamingo Distributed Checkpointing
- Principle:Microsoft Autogen Swarm Execution
- Principle:Fede1024 Rust rdkafka FFI Binding Layer
- Principle:Mlfoundations Open flamingo Pretrained Weight Loading
- Principle:Guardrails ai Guardrails Validator Logic Implementation
- Principle:Volcengine Verl Prompt Template Design
- Principle:Triton inference server Server Ensemble Pipeline Testing
Implementations
- Implementation:Bentoml BentoML SyncHTTPClient For Cloud
- Implementation:TobikoData Sqlmesh Editor Context
- Implementation:LMCache LMCache LMCacheControllerManager Init
- Implementation:Alibaba MNN Protobuf Extension Set H
- Implementation:Ucbepic Docetl Dataset Medical Transcripts
- Implementation:Hpcaitech ColossalAI Generate With Actor
- Implementation:Infiniflow Ragflow UserCanvasService Save
- Implementation:Alibaba MNN RapidJSON Stdint
- Implementation:Spcl Graph of thoughts KeywordCountingPrompter
- Implementation:EvolvingLMMs Lab Lmms eval StructEditBench 2Stage Eval
Heuristics
- Heuristic:Hiyouga LLaMA Factory Quantized Training Best Practices
- Heuristic:EvolvingLMMs Lab Lmms eval Limit Flag Testing Only
- Heuristic:ChenghaoMou Text dedup Bloom Filter Single Process
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
- Heuristic:Shiyu coder Kronos Sampling Temperature Tuning
- Heuristic:Mlflow Mlflow Nested Run Organization
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix CuDNN Benchmark Scale Width
- Heuristic:Hpcaitech ColossalAI Empty Cache Between Phases
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:Microsoft Autogen Parallel Tool Call Safety
Environments
- Environment:Helicone Helicone Python ClickHouse Migrations
- Environment:Duckdb Duckdb Code Generation Tools
- Environment:Pyro ppl Pyro Funsor Backend
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:DataTalksClub Data engineering zoomcamp Docker PostgreSQL Python Environment
- Environment:Huggingface Diffusers Training Environment
- Environment:Kubeflow Kubeflow Istio Certmanager Dex Environment
- Environment:Pola rs Polars GPU Execution Environment
- Environment:Ggml org Llama cpp Metal GPU Environment
- Environment:Ucbepic Docetl Python Runtime