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:Puppeteer Puppeteer Request Interception
- Workflow:Speechbrain Speechbrain Whisper ASR Finetuning
- Workflow:OpenBMB UltraFeedback Dataset Construction
- Workflow:Bentoml BentoML BentoCloud Deployment
- Workflow:BerriAI Litellm Response Caching
- Workflow:Neuml Txtai Pipeline Workflow Chaining
- Workflow:Groq Groq python Text To Speech
- Workflow:BerriAI Litellm Proxy Server Deployment
- Workflow:OpenGVLab InternVL Benchmark Evaluation
- Workflow:Langfuse Langfuse Evaluation pipeline
Principles
- Principle:Recommenders team Recommenders Chronological Data Splitting
- Principle:Openclaw Openclaw Documentation Site Configuration
- Principle:Ollama Ollama Tool Call Parsing
- Principle:Getgauge Taiko Gauge Project Setup
- Principle:Openai Openai python Image Generation Parameters
- Principle:Ollama Ollama Adapter Conversion
- Principle:ClickHouse ClickHouse Wide Integer Arithmetic
- Principle:Danijar Dreamerv3 Data Collection And Training
- Principle:Apache Spark YARN Web Proxy Security
- Principle:Tensorflow Tfjs Transformer Backbone Construction
Implementations
- Implementation:Ollama Ollama Llama Grammar
- Implementation:Iterative Dvc Find Targets And Create Stage
- Implementation:EvolvingLMMs Lab Lmms eval VLMs Are Biased Utils
- Implementation:Openclaw Openclaw HealthCommand
- Implementation:CARLA simulator Carla InMemoryMap
- Implementation:Langgenius Dify Component Analyzer
- Implementation:Bentoml BentoML CLI Api Token
- Implementation:Zai org CogVideo Caption File Output
- Implementation:Vllm project Vllm CPU Attn NEON
- Implementation:Kserve Kserve InferenceGraph CRD Spec
Heuristics
- Heuristic:Gretelai Gretel synthetics Binary Encoder Cutoff
- Heuristic:Lucidrains X transformers Rotary Position Embedding Selection
- Heuristic:Sktime Pytorch forecasting Batch Size Selection
- Heuristic:ArroyoSystems Arroyo Parallelism Configuration
- Heuristic:MaterializeInc Materialize CI Agent Prioritization
- Heuristic:Microsoft Autogen Name Uniqueness Constraints
- Heuristic:Apache Airflow Scheduler Performance Tuning
- Heuristic:PacktPublishing LLM Engineers Handbook Temperature Selection By Task
- Heuristic:Onnx Onnx Warning Deprecated InlineSelectedFunctions
- Heuristic:Fastai Fastbook Embedding Size Rule
Environments
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:Google deepmind Mujoco MJX JAX Environment
- Environment:Allenai Open instruct Python 3 12 Runtime
- Environment:Webdriverio Webdriverio Browser Driver Environment
- Environment:Mlflow Mlflow Docker Container Environment
- Environment:Intel Ipex llm NPU Environment
- Environment:Mit han lab Llm awq VILA Multimodal Environment
- Environment:Facebookresearch Audiocraft Python PyTorch CUDA Environment
- Environment:Mlc ai Mlc llm WebGPU Browser Environment
- Environment:Allenai Open instruct vLLM Inference