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:Helicone Helicone LLM Response Normalization
- Workflow:Microsoft Playwright Browser automation CLI
- Workflow:Ggml org Llama cpp Multimodal Inference
- Workflow:Langgenius Dify Plugin Management
- Workflow:Iterative Dvc Plot Visualization
- Workflow:Google deepmind Dm control Locomotion Task Setup
- Workflow:TobikoData Sqlmesh Dbt project migration
- Workflow:Anthropics Anthropic sdk python Extended Thinking Reasoning
- Workflow:Tencent Ncnn Post Training Quantization
- Workflow:Huggingface Transformers Pipeline Inference
Principles
- Principle:Ray project Ray Named Actor Retrieval
- Principle:Puppeteer Puppeteer Browser Process Management
- Principle:Tensorflow Tfjs Model Format Conversion
- Principle:Zai org CogVideo Perceptual Adversarial Loss
- Principle:Apache Paimon Blob Metadata Writing
- Principle:Huggingface Datasets JSON Import
- Principle:Fede1024 Rust rdkafka Manual Offset Management
- Principle:Openai Whisper Word Boundary Detection
- Principle:Microsoft Onnxruntime ORT Accelerated Training
- Principle:Openclaw Openclaw Channel Setup
Implementations
- Implementation:BerriAI Litellm Logging Callback Manager
- Implementation:Cohere ai Cohere python ToolCall Model
- Implementation:Microsoft Autogen Studio Environment Settings
- Implementation:OpenGVLab InternVL InternVLConfig LLaVA
- Implementation:Apache Shardingsphere YamlShadowRuleConfiguration Structure
- Implementation:Predibase Lorax Chat Completion Request
- Implementation:Predibase Lorax MLlama Wrapper
- Implementation:Testtimescaling Testtimescaling github io Actions Checkout V3
- Implementation:BerriAI Litellm Aporia AI Guardrail
- Implementation:Sgl project Sglang CPU Decode Attention
Heuristics
- Heuristic:Guardrails ai Guardrails Sentence Tokenizer Optimization
- Heuristic:SeleniumHQ Selenium Warning Deprecated HasDownloads GetDownloadableFiles
- Heuristic:Norrrrrrr lyn WAInjectBench NaN Inf Fallback FP32 Recovery
- Heuristic:Trailofbits Fickling Force Flag Bypass
- Heuristic:Lm sys FastChat Greedy Decoding Temperature Threshold
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Microsoft Playwright Test Stability Practices
- Heuristic:Openai Openai agents python GPT 5 Reasoning Settings
- Heuristic:Mlfoundations Open flamingo FSDP Manual Wrapping For Mixed Parameters
- Heuristic:Onnx Onnx Shape Inference Limitations
Environments
- Environment:Intel Ipex llm XPU Finetuning Environment
- Environment:Ucbepic Docetl Frontend Node Environment
- Environment:Kornia Kornia PyTorch Python Environment
- Environment:Microsoft BIPIA Python CUDA GPU Environment
- Environment:Deepspeedai DeepSpeed NVMe Environment
- Environment:Helicone Helicone Docker Compose Infrastructure
- Environment:Sgl project Sglang ROCm
- Environment:Neuml Txtai Optional Extras Dependencies
- Environment:Openai Whisper PyTorch CUDA
- Environment:Langchain ai Langchain Python 3 10 Runtime