Main Page
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:AnswerDotAI RAGatouille Document Indexing And Search
- Workflow:Alibaba ROLL Agentic RL Training Pipeline
- Workflow:Truera Trulens RAG Evaluation With LangChain
- Workflow:Tencent Ncnn Image Classification Inference
- Workflow:AUTOMATIC1111 Stable diffusion webui Textual inversion training
- Workflow:Mit han lab Llm awq HuggingFace Model Export
- Workflow:Anthropics Anthropic sdk python Cloud Provider Deployment
- Workflow:Bitsandbytes foundation Bitsandbytes 8bit Optimizer Training
- Workflow:Vespa engine Vespa Document indexing pipeline
- Workflow:Apache Shardingsphere Dynamic Rule Configuration Change
Principles
- Principle:Kserve Kserve PD Scheduler Routing
- Principle:Haosulab ManiSkill Sim2Real Bridge
- Principle:Openclaw Openclaw Persona Customization
- Principle:Bentoml BentoML Runtime Environment Definition
- Principle:Online ml River Streaming ROCAUC
- Principle:Ollama Ollama APIDesign
- Principle:Tensorflow Tfjs Weight Constraints
- Principle:Mlfoundations Open flamingo FSDP Model Wrapping
- Principle:NVIDIA NeMo Aligner DPO Sequence Packing
- Principle:Risingwavelabs Risingwave CDC Source Validation
Implementations
- Implementation:Mlc ai Mlc llm Radix Tree Header
- Implementation:Haosulab ManiSkill PickSingleYCB
- Implementation:Apache Paimon FormatReadBuilder
- Implementation:Datajuicer Data juicer ArxivDownloader
- Implementation:Kserve Kserve LLM Decode Worker DP Config
- Implementation:NVIDIA NeMo Curator KMeansStage
- Implementation:Togethercomputer Together python Videos Create
- Implementation:Huggingface Datasets TenBin
- Implementation:Hiyouga LLaMA Factory Model Adapter
- Implementation:Ollama Ollama MLXRunner MLX Generated H
Heuristics
- Heuristic:Kubeflow Pipelines Resource Sizing For Components
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:Ggml org Llama cpp Quantization Quality Tips
- Heuristic:Turboderp org Exllamav2 Memory Optimization Techniques
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Gretelai Gretel synthetics Gumbel Softmax NaN Retry
- Heuristic:Roboflow Rf detr Batch Size Memory Tradeoff
- Heuristic:Huggingface Open r1 Distributed Training Configuration
- Heuristic:Dagster io Dagster Record Over Dataclass
- Heuristic:Avhz RustQuant MC Parallel Path Threshold
Environments
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Webdriverio Webdriverio Browser Driver Environment
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:EvolvingLMMs Lab Lmms eval Server Mode Environment
- Environment:Lakeraai Pint benchmark Python 310 With Transformers
- Environment:Openai Whisper Numba
- Environment:Apache Dolphinscheduler Netty Runtime
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Neuml Txtai Optional Extras Dependencies
- Environment:PacktPublishing LLM Engineers Handbook Unsloth Finetuning Environment