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:Isaac sim IsaacGymEnvs RL Policy Training
- Workflow:TA Lib Ta lib python Candlestick Pattern Recognition
- Workflow:Romsto Speculative Decoding Interactive CLI Comparison
- Workflow:Sgl project Sglang Online Serving With OpenAI API
- Workflow:Wandb Weave LLM Integration Tracing
- Workflow:Openai Openai python Chat Completion
- Workflow:Helicone Helicone Integrate Provider To Gateway
- Workflow:Bentoml BentoML Multi Model Composition
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:AUTOMATIC1111 Stable diffusion webui Image postprocessing and upscaling
Principles
- Principle:Recommenders team Recommenders Negative Sampling For Implicit Feedback
- Principle:SeldonIO Seldon core Model Resource Definition
- Principle:Google deepmind Mujoco Analytical Derivatives
- Principle:Rapidsai Cuml Forest Inference
- Principle:HKUDS AI Trader Frontend Cache Management
- Principle:Langchain ai Langgraph Edge Configuration
- Principle:TA Lib Ta lib python Stream Event Integration
- Principle:AUTOMATIC1111 Stable diffusion webui Memory Management
- Principle:BerriAI Litellm Error Handling
- Principle:Protectai Llm guard Regex Pattern Matching
Implementations
- Implementation:Infiniflow Ragflow Embedding Function
- Implementation:Online ml River Stats Mean
- Implementation:Princeton nlp Tree of thought llm Get Task Factory
- Implementation:NVIDIA NeMo Curator ModelStage
- Implementation:Ollama Ollama Llama Common Header
- Implementation:CARLA simulator Carla RPC Texture
- Implementation:FlowiseAI Flowise LoginActivity
- Implementation:Mlfoundations Open flamingo Evaluate captioning
- Implementation:Arize ai Phoenix Evals Public API
- Implementation:Ollama Ollama Anthropic Handler
Heuristics
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:Pytorch Serve LLM Timeout Configuration
- Heuristic:OpenRLHF OpenRLHF Adam Offload Memory Tip
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:ThreeSR Awesome Inference Time Scaling API Rate Limiting Tip
- Heuristic:Lance format Lance IO Buffer And Batch Sizing
- Heuristic:Unstructured IO Unstructured Multi Python Matrix
- Heuristic:Farama Foundation Gymnasium Render Mode Selection Guide
- Heuristic:Bitsandbytes foundation Bitsandbytes Compute Dtype Mismatch Warning
- Heuristic:Pola rs Polars Avoid Lambda In Aggregation
Environments
- Environment:Evidentlyai Evidently LLM Evaluation Environment
- Environment:Guardrails ai Guardrails Docker Server Runtime
- Environment:Volcengine Verl Ray Distributed Environment
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:OpenBMB UltraFeedback OpenAI API Environment
- Environment:Eric mitchell Direct preference optimization Python Dependencies
- Environment:Openai Whisper FFmpeg
- Environment:Promptfoo Promptfoo Browser Automation
- Environment:Mlfoundations Open flamingo HuggingFace Open CLIP Dependencies
- Environment:Explodinggradients Ragas Optional Metrics Environment