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:Dotnet Machinelearning ONNX Model Scoring
- Workflow:FlagOpen FlagEmbedding Embedder Finetuning
- Workflow:MaterializeInc Materialize CI Pipeline Generation
- Workflow:VainF Torch Pruning Vision Transformer Pruning
- Workflow:Heibaiying BigData Notes Storm Topology Development
- Workflow:Neuml Txtai Semantic Search Pipeline
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Unslothai Unsloth GRPO Reinforcement Learning
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:Anthropics Anthropic sdk python Tool Use Integration
Principles
- Principle:Openai Openai agents python Bidirectional Handoffs
- Principle:SqueezeAILab ETS ILP Node Selection
- Principle:Marker Inc Korea AutoRAG Answer Generation
- Principle:Bigscience workshop Petals Block Selection
- Principle:Risingwavelabs Risingwave CDC Schema History
- Principle:Huggingface Datatrove Language Filtering
- Principle:Anthropics Anthropic sdk python Response Processing
- Principle:Eventual Inc Daft Arrow FFI Compatibility
- Principle:Anthropics Anthropic sdk python Stream Context Manager Setup
- Principle:ArroyoSystems Arroyo Job Monitoring
Implementations
- Implementation:Kserve Kserve LLMInferenceService CRD Spec
- Implementation:TobikoData Sqlmesh ModelName
- Implementation:Speechbrain Speechbrain GigaSpeech Dataset
- Implementation:Langfuse Langfuse ChatML Types
- Implementation:CARLA simulator Carla VehiclePhysicsControl
- Implementation:Bitsandbytes foundation Bitsandbytes Python Package CI Workflow
- Implementation:Open compass VLMEvalKit WorldSense Utils
- Implementation:Microsoft Autogen Studio Model Fields
- Implementation:OpenHands OpenHands SaaSExperimentManager
- Implementation:NVIDIA DALI FITS Parser
Heuristics
- Heuristic:Langchain ai Langgraph Stream Mode Selection
- Heuristic:Tensorflow Tfjs WebGL Shader Warmup
- Heuristic:Huggingface Optimum Version Conditional Behavior
- Heuristic:Gretelai Gretel synthetics Gumbel Softmax NaN Retry
- Heuristic:AUTOMATIC1111 Stable diffusion webui Cross Attention Memory Slicing
- Heuristic:Avhz RustQuant Finite Difference Grid Sizing
- Heuristic:MaterializeInc Materialize CI Retry Strategies
- Heuristic:ArroyoSystems Arroyo Parallelism Configuration
- Heuristic:Triton inference server Server Concurrency Throughput Rule
- Heuristic:Alibaba MNN LLM Runtime Tuning
Environments
- Environment:Openai Openai python Realtime WebSocket
- Environment:OpenBMB UltraFeedback Python GPU Environment
- Environment:NVIDIA NeMo Curator Video Codec Stack
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:Kserve Kserve Kubernetes Cluster
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:Pyro ppl Pyro Visualization Tools
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:Mlfoundations Open flamingo HuggingFace Open CLIP Dependencies
- Environment:Junyanz Pytorch CycleGAN and pix2pix Python PyTorch Runtime