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:Huggingface Peft LoRA Causal LM Finetuning
- Workflow:Google research Deduplicate text datasets Suffix array querying
- Workflow:CrewAIInc CrewAI Hierarchical Crew Execution
- Workflow:Ollama Ollama Model Registry Operations
- Workflow:Togethercomputer Together python Chat Completion
- Workflow:Pytorch Serve LLM Deployment vLLM
- Workflow:Huggingface Datasets Dataset Streaming
- Workflow:Pola rs Polars Streaming Large Dataset Processing
- Workflow:Liu00222 Open Prompt Injection Prompt Injection Experiment
- Workflow:NVIDIA NeMo Curator Semantic Deduplication
Principles
- Principle:Datahub project Datahub CLI Installation For Docker
- Principle:Google deepmind Mujoco Restrict Optimization
- Principle:Haosulab ManiSkill Reward Success Design
- Principle:Dotnet Machinelearning Text Featurization
- Principle:Apache Druid Partitioning Configuration
- Principle:Cypress io Cypress Launchpad Initialization
- Principle:Apache Beam Pipeline Construction
- Principle:Volcengine Verl Package Initialization
- Principle:NVIDIA NeMo Curator File Partitioning
- Principle:Hpcaitech ColossalAI Text Splitting Chunking
Implementations
- Implementation:Sgl project Sglang CPU GEMM FP8
- Implementation:Tencent Ncnn Extractor Input And Extract
- Implementation:Kornia Kornia ZCA Whitening
- Implementation:Ggml org Ggml Download ggml model
- Implementation:Turboderp org Exllamav2 ExLlamaV2WebSocketServer
- Implementation:Trailofbits Fickling Deactivate Safe ML Environment
- Implementation:ArroyoSystems Arroyo Wait For State
- Implementation:Facebookresearch Habitat lab Observations to image
- Implementation:Hiyouga LLaMA Factory Data Converter
- Implementation:MaterializeInc Materialize ResolvedImage Build
Heuristics
- Heuristic:DistrictDataLabs Yellowbrick Scikit Learn API Compatibility
- Heuristic:Apache Spark Partition Sizing Tips
- Heuristic:Dagster io Dagster Record Over Dataclass
- Heuristic:Openclaw Openclaw WebSocket Reconnection And Session Cleanup
- Heuristic:Ggml org Ggml Thread Count Selection
- Heuristic:Predibase Lorax Quantization Backend Selection
- Heuristic:Tencent Ncnn Optimize Before Quantize
- Heuristic:Groq Groq python Timeout Configuration
- Heuristic:Unstructured IO Unstructured PDF Element Sorting
- Heuristic:Mlc ai Web llm KV Cache Window Configuration
Environments
- Environment:Huggingface Datasets JAX Integration
- Environment:Interpretml Interpret Blackbox Explainer Dependencies
- Environment:Duckdb Duckdb Code Formatting Tools
- Environment:Scikit learn contrib Imbalanced learn Keras TensorFlow
- Environment:Tencent Ncnn Build Environment
- Environment:Ggml org Ggml Vulkan GPU Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Apache Druid Web Console Development
- Environment:Kserve Kserve Knative Serving
- Environment:Alibaba ROLL Diffusion Video Environment