Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Wandb Weave Prompt Management
- Workflow:OpenGVLab InternVL LoRA Finetuning
- Workflow:Tensorflow Serving REST API Inference
- Workflow:Alibaba ROLL DPO Training Pipeline
- Workflow:Scikit learn Scikit learn Ensemble Model Building
- Workflow:OpenHands OpenHands Third Party Runtime Integration
- Workflow:Huggingface Diffusers ControlNet Guided Generation
- Workflow:Spcl Graph of thoughts GoT Document Merging Pipeline
- Workflow:Cleanlab Cleanlab Classification Label Issue Detection
- Workflow:Fastai Fastbook Neural Network From Scratch
Principles
- Principle:Eric mitchell Direct preference optimization Preference Data Format
- Principle:Allenai Open instruct DPO Training
- Principle:Groq Groq python API Error Response Structure
- Principle:Pytorch Serve Multimodal Inference
- Principle:AUTOMATIC1111 Stable diffusion webui Sampling Architecture
- Principle:Langfuse Langfuse Ingestion Queue Dispatch
- Principle:OWASP Www project top 10 for large language model applications Agentic Architecture Mapping
- Principle:LaurentMazare Tch rs Adam Optimization
- Principle:Fastai Fastbook Model Export
- Principle:Neuml Txtai Tool Assembly
Implementations
- Implementation:Sgl project Sglang Program State Fork Join
- Implementation:CARLA simulator Carla Agent Misc Utils
- Implementation:LMCache LMCache External Connector Adapter
- Implementation:Ollama Ollama Imagegen Flux2 Transformer
- Implementation:Speechbrain Speechbrain Hparams Switchboard Transformer LM
- Implementation:Openai Openai python API Resource Base
- Implementation:Openai Openai python API Error Hierarchy
- Implementation:Puppeteer Puppeteer PSelectorParser
- Implementation:ARISE Initiative Robosuite RethinkGripper
- Implementation:Open compass VLMEvalKit Register Dataset
Heuristics
- Heuristic:Huggingface Open r1 Code Execution Timeout Strategy
- Heuristic:Iamhankai Forest of Thought Input Length Overflow Recovery
- Heuristic:Treeverse LakeFS Retry Backoff Configuration
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Vespa engine Vespa Config Polling Timeout Tuning
- Heuristic:Astronomer Astronomer cosmos Static Parser Hang Workaround
- Heuristic:Explodinggradients Ragas Concurrency And Rate Limiting
- Heuristic:Ggml org Ggml Memory Allocation Strategy
- Heuristic:Isaac sim IsaacGymEnvs DR Setup Only Flag
- Heuristic:Norrrrrrr lyn WAInjectBench NaN Inf Fallback FP32 Recovery
Environments
- Environment:Pyro ppl Pyro Distributed Training
- Environment:ARISE Initiative Robomimic Robosuite Simulation Backend
- Environment:Unstructured IO Unstructured Libmagic
- Environment:Tencent Ncnn Build Environment
- Environment:Langchain ai Langchain LangSmith Tracing Config
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Deepseek ai Janus JanusFlow Diffusers Environment
- Environment:Datajuicer Data juicer Python Runtime Environment
- Environment:Shiyu coder Kronos HuggingFace Hub Access
- Environment:Huggingface Optimum GPTQ Quantization Environment