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:Ggml org Llama cpp Multimodal Inference
- Workflow:Guardrails ai Guardrails LLM Output Validation
- Workflow:Rapidsai Cuml Time Series Forecasting
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:Tensorflow Serving Model Version Management
- Workflow:Langgenius Dify App Creation and Configuration
- Workflow:Axolotl ai cloud Axolotl Full Finetuning Distributed
- Workflow:Online ml River Drift Adaptive Classification
- Workflow:Huggingface Datatrove Common Crawl Processing
- Workflow:Princeton nlp SimPO SimPO Training
Principles
- Principle:CARLA simulator Carla Python API Build
- Principle:Datahub project Datahub Lineage Emission
- Principle:Axolotl ai cloud Axolotl Tokenizer Configuration
- Principle:Openai Openai python Structured Output Definition
- Principle:NVIDIA NeMo Curator Pairwise Similarity Computation
- Principle:Onnx Onnx Model Serialization
- Principle:VainF Torch Pruning Model Complexity Profiling
- Principle:CARLA simulator Carla Walker AI Control
- Principle:Huggingface Datasets Column Removal
- Principle:Cleanlab Cleanlab Datalab Regression Label Issue Detection
Implementations
- Implementation:Run llama Llama index Tool Calling
- Implementation:Diagram of thought Diagram of thought Graphviz DAG Visualization
- Implementation:Run llama Llama index BatchEvalRunner Evaluate Queries
- Implementation:Mage ai Mage ai Buildkite ECS Deploy
- Implementation:ARISE Initiative Robosuite WheeledRobot
- Implementation:Treeverse LakeFS RunSparkSubmit
- Implementation:Pyro ppl Pyro SV DKL
- Implementation:TobikoData Sqlmesh Graph Context
- Implementation:Evidentlyai Evidently Legacy Collector Config
- Implementation:Mlc ai Mlc llm Fuse FT Dequantize Matmul Epilogue
Heuristics
- Heuristic:Google deepmind Dm control Tolerance Reward Tuning
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Identity Loss Color Preservation
- Heuristic:CrewAIInc CrewAI LLM Provider Message Workarounds
- Heuristic:AUTOMATIC1111 Stable diffusion webui UNet Performance Patches
- Heuristic:EvolvingLMMs Lab Lmms eval Truncated Image Handling
- Heuristic:Predibase Lorax Flash Attention Backend Selection
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
- Heuristic:CarperAI Trlx KL Coefficient Adaptation
- Heuristic:Mistralai Client python Retry Backoff Strategy
- Heuristic:Elevenlabs Elevenlabs python Client Timeout Configuration
Environments
- Environment:AnswerDotAI RAGatouille Python ColBERT Dependencies
- Environment:Allenai Open instruct Python 3 12 Runtime
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Sgl project Sglang CUDA
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Haifengl Smile Native BLAS LAPACK ARPACK
- Environment:Langgenius Dify Docker Compose Environment
- Environment:Shiyu coder Kronos DDP Multi GPU Environment
- Environment:Mit han lab Llm awq Python Runtime Environment
- Environment:Datahub project Datahub Frontend Build