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:Eric mitchell Direct preference optimization SFT Training
- Workflow:Haifengl Smile Matrix Decomposition Pipeline
- Workflow:Googleapis Python genai Multimodal Content Generation
- Workflow:Mbzuai oryx Awesome LLM Post training Research Trend Analysis
- Workflow:MarketSquare Robotframework browser Library Development and Release
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
- Workflow:Guardrails ai Guardrails Custom Validator Development
- Workflow:Axolotl ai cloud Axolotl Full Finetuning Distributed
- Workflow:Arize ai Phoenix Dataset and Experiment Lifecycle
- Workflow:Cohere ai Cohere python Semantic Search With Rerank
Principles
- Principle:Speechbrain Speechbrain Beam Search Decoding
- Principle:Lance format Lance Data Scanning And Reading
- Principle:BerriAI Litellm Fine Tuned Model Usage
- Principle:Triton inference server Server TensorRT Engine Build
- Principle:Shiyu coder Kronos Predictor Initialization
- Principle:Facebookresearch Audiocraft Temporal Conditioning Preparation
- Principle:Ggml org Llama cpp PEG Parser Framework
- Principle:Avhz RustQuant Exotic Option Contracts
- Principle:CarperAI Trlx Synthetic Environment Design
- Principle:Openai Evals Eval Resolution
Implementations
- Implementation:Facebookresearch Habitat lab Habitat Lab Tutorial
- Implementation:Online ml River Datasets MovieLens100K
- Implementation:Microsoft Agent framework Response Handler Decorator
- Implementation:TobikoData Sqlmesh Model Directory
- Implementation:Arize ai Phoenix Score Dataclass
- Implementation:Online ml River Imblearn RandomSampler
- Implementation:Promptfoo Promptfoo createDummyFiles
- Implementation:Romsto Speculative Decoding Tokenizer Apply Chat Template
- Implementation:Rapidsai Cuml Treelite Integration
- Implementation:Interpretml Interpret Tensor Hpp
Heuristics
- Heuristic:Langgenius Dify SQL Escape Backslash First
- Heuristic:Apache Dolphinscheduler HikariCP Pool Tuning
- Heuristic:Marker Inc Korea AutoRAG Deterministic Evaluation Generation
- Heuristic:Lance format Lance Warning Deprecated Java APIs
- Heuristic:Evidentlyai Evidently Statistical Test Auto Selection
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Princeton nlp SimPO Concatenated Forward Pass
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
- Heuristic:Huggingface Transformers Dataloader Pin Memory NonBlocking
- Heuristic:ClickHouse ClickHouse Test Writing Conventions
Environments
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:Kserve Kserve Knative Serving
- Environment:Hiyouga LLaMA Factory Core Python GPU Environment
- Environment:Nightwatchjs Nightwatch Selenium WebDriver 4
- Environment:Treeverse LakeFS Web UI Environment
- Environment:Kubeflow Kubeflow Kubernetes Cluster Environment
- Environment:Bitsandbytes foundation Bitsandbytes XPU SYCL Runtime
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment