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:Allenai Open instruct GRPO Reinforcement Learning
- Workflow:Mage ai Mage ai Building a New Destination Connector
- Workflow:Diagram of thought Diagram of thought DoT Trace Extraction
- Workflow:Pyro ppl Pyro Bayesian Regression
- Workflow:ChenghaoMou Text dedup Suffix Array Deduplication
- Workflow:Ggml org Llama cpp Embedding Extraction
- Workflow:Openai Openai node Chat Completion
- Workflow:Togethercomputer Together python Embeddings And Reranking
- Workflow:Iterative Dvc Data Tracking
- Workflow:Lm sys FastChat Vicuna SFT Finetuning
Principles
- Principle:Webdriverio Webdriverio CapabilityNormalization
- Principle:Huggingface Transformers Pipeline Forward Pass
- Principle:Wandb Weave Distribution Build
- Principle:Datajuicer Data juicer Column Wise Distribution Analysis
- Principle:OWASP Www project top 10 for large language model applications Manual Adversarial Testing
- Principle:Haosulab ManiSkill Reward Success Design
- Principle:EvolvingLMMs Lab Lmms eval LLM as Judge
- Principle:Apache Shardingsphere MetaData Context Creation
- Principle:LLMBook zh LLMBook zh github io LoRA Adapter Merging
- Principle:Volcengine Verl GAE Advantage Estimation
Implementations
- Implementation:Run llama Llama index BaseSelector
- Implementation:Ollama Ollama Llama Core
- Implementation:BerriAI Litellm Exception Mapping
- Implementation:Ollama Ollama Llama Graph Header
- Implementation:Cohere ai Cohere python NonStreamedChatResponse Model
- Implementation:Triton inference server Server L0 Model Namespacing Test
- Implementation:Langfuse Langfuse Score Application Validation
- Implementation:Langgenius Dify FetchCollectionList
- Implementation:NVIDIA NeMo Curator ClipFrameExtractionStage
- Implementation:NVIDIA DALI NumPy Header
Heuristics
- Heuristic:Iamhankai Forest of Thought Early Stop Majority Vote
- Heuristic:Microsoft DeepSpeedExamples RLHF Hyperparameter Guide
- Heuristic:NVIDIA TransformerEngine Attention Backend Selection
- Heuristic:NVIDIA TransformerEngine Build Optimization Tips
- Heuristic:Openclaw Openclaw Plugin Dependency Gotchas
- Heuristic:Turboderp org Exllamav2 Memory Optimization Techniques
- Heuristic:Mlflow Mlflow Async Logging Best Practices
- Heuristic:Datahub project Datahub Git Worktree Gradle Fix
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
Environments
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:EvolvingLMMs Lab Lmms eval Python Runtime Environment
- Environment:EvolvingLMMs Lab Lmms eval Server Mode Environment
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention
- Environment:Google deepmind Dm control OSMesa Software Rendering
- Environment:Deepspeedai DeepSpeed NVMe Environment
- Environment:Kornia Kornia PyTorch Python Environment
- Environment:ChenghaoMou Text dedup Python 3 12 Environment
- Environment:Langgenius Dify Vector Database Environment
- Environment:Junyanz Pytorch CycleGAN and pix2pix Python PyTorch Runtime