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:Microsoft Semantic kernel Plugin Integration And Function Calling
- Workflow:Turboderp org Exllamav2 Multimodal Vision Inference
- Workflow:Langgenius Dify Plugin Installation and Configuration
- Workflow:Mistralai Client python Text Embeddings
- Workflow:Fastai Fastbook Image Classification
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:Openai CLIP Linear probe evaluation
- Workflow:Tensorflow Serving REST API Inference
- Workflow:Huggingface Open r1 Model Evaluation
- Workflow:Microsoft LoRA GPT2 NLG Finetuning
Principles
- Principle:Huggingface Datasets AudioFolder Dataset Building
- Principle:Apache Kafka Artifact Signing
- Principle:EvolvingLMMs Lab Lmms eval Dataset Preparation
- Principle:Ollama Ollama CLIArchitecture
- Principle:Langgenius Dify UserSettings
- Principle:Hiyouga LLaMA Factory Distributed Training
- Principle:Neuml Txtai Graph Network
- Principle:Speechbrain Speechbrain Brain Subclass Initialization
- Principle:VainF Torch Pruning Hessian Importance
- Principle:Googleapis Python genai History Management
Implementations
- Implementation:Onnx Onnx Doc Strings Generator
- Implementation:Speechbrain Speechbrain Prepare GigaSpeech Root
- Implementation:Allenai Open instruct WorkerWrap
- Implementation:Ray project Ray MetricConfig
- Implementation:Openai Openai python Response Image Gen Call Generating
- Implementation:FlowiseAI Flowise ToolsView
- Implementation:Microsoft Playwright APIRequestContext Fetch
- Implementation:ContextualAI HALOs BasicTrainer Save
- Implementation:LMCache LMCache Config Base
- Implementation:Haifengl Smile StructType
Heuristics
- Heuristic:Onnx Onnx Opset Version Selection
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
- Heuristic:Lucidrains X transformers Sampling Temperature Strategy
- Heuristic:Fastai Fastbook Weight Decay Tuning
- Heuristic:Facebookresearch Audiocraft Gradient Balancing For Multi Loss
- Heuristic:Openclaw Openclaw WebSocket Reconnection And Session Cleanup
- Heuristic:CarperAI Trlx Batch Size Tuning
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Pola rs Polars Lazy Over Eager Preference
Environments
- Environment:Microsoft BIPIA Python CUDA GPU Environment
- Environment:Vllm project Vllm Distributed
- Environment:Iterative Dvc Python Runtime
- Environment:Huggingface Datatrove Slurm Cluster Environment
- Environment:Microsoft Autogen Studio Server Environment
- Environment:Cohere ai Cohere python Cohere API Credentials
- Environment:Googleapis Python genai Python 3 10 SDK Runtime
- Environment:Rapidsai Cuml CUDA GPU
- Environment:Tensorflow Serving Docker Runtime Environment
- Environment:BerriAI Litellm Docker Deployment