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:Neuml Txtai Agent Execution
- Workflow:InternLM Lmdeploy LLM Offline Batch Inference
- Workflow:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:Unslothai Unsloth Model Export And Deployment
- Workflow:Diagram of thought Diagram of thought DoT Trace Extraction
- Workflow:AUTOMATIC1111 Stable diffusion webui Hypernetwork training
- Workflow:SeldonIO Seldon core Production Monitoring Pipeline
- Workflow:OpenRLHF OpenRLHF Math Reasoning Training
- Workflow:Bentoml BentoML BentoCloud Deployment
- Workflow:Ggml org Llama cpp HF to GGUF Model Conversion
Principles
- Principle:Eventual Inc Daft UDF Metrics
- Principle:Apache Dolphinscheduler Workflow Triggering
- Principle:Deepset ai Haystack In Memory Document Storage
- Principle:Langchain ai Langchain Standard Integration Testing
- Principle:Huggingface Datasets In Place Format Setting
- Principle:Gretelai Gretel synthetics GAN Adversarial Training
- Principle:NVIDIA DALI Custom Operator Build System
- Principle:Lm sys FastChat LLM Judge Evaluation
- Principle:Protectai Llm guard PII Deanonymization
- Principle:Eric mitchell Direct preference optimization Concatenated Inputs
Implementations
- Implementation:Gretelai Gretel synthetics Tokenizer Training Pipeline
- Implementation:Elevenlabs Elevenlabs python VerificationAttemptResponse
- Implementation:FlowiseAI Flowise MultiDropdown
- Implementation:Deepspeedai DeepSpeed Evoformer Bias Broadcast
- Implementation:Evidentlyai Evidently LLM Models
- Implementation:Online ml River Sketch Counter
- Implementation:Google deepmind Mujoco USD MJCF File Format
- Implementation:Avhz RustQuant Distribution Trait
- Implementation:Google deepmind Mujoco MJX Mesh
- Implementation:Predibase Lorax Tensor Parallel Layers
Heuristics
- Heuristic:Trailofbits Fickling Allowlist Maintenance
- Heuristic:Apache Airflow Memory Management Tips
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Cleanlab Cleanlab Label Quality Scoring Method Selection
- Heuristic:Tencent Ncnn Letterbox Vs Direct Resize
- Heuristic:Liu00222 Open Prompt Injection Cosine Similarity Segmentation Threshold
- Heuristic:Roboflow Rf detr Layer Wise LR Decay
- Heuristic:DataTalksClub Data engineering zoomcamp Dbt Materialization Strategy
- Heuristic:Apache Hudi Compaction Scheduling Safety
- Heuristic:Langgenius Dify API Token Single Flight Caching
Environments
- Environment:Ggml org Llama cpp Metal GPU Environment
- Environment:Predibase Lorax Model Source Credentials
- Environment:Testtimescaling Testtimescaling github io Python 3 Runtime
- Environment:Run llama Llama index OpenAI API Configuration
- Environment:Tensorflow Serving Docker Runtime Environment
- Environment:Sgl project Sglang CUDA SM100
- Environment:Sgl project Sglang Runtime
- Environment:FlagOpen FlagEmbedding GPU Accelerator Environment
- Environment:DataTalksClub Data engineering zoomcamp Kestra Orchestration Environment
- Environment:Unstructured IO Unstructured PDF Dependencies