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:CARLA simulator Carla Simulation Recording and Replay
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Langfuse Langfuse Trace ingestion pipeline
- Workflow:Vllm project Vllm OpenAI Compatible Serving
- Workflow:Marker Inc Korea AutoRAG Pipeline Deployment
- Workflow:Haotian liu LLaVA LoRA Finetuning
- Workflow:Tencent Ncnn Object Detection Inference
- Workflow:Mlflow Mlflow Model Logging and Registry
- Workflow:Huggingface Alignment handbook ORPO Single Stage Alignment
Principles
- Principle:InternLM Lmdeploy Image Loading
- Principle:Guardrails ai Guardrails Guard Validator Composition
- Principle:Speechbrain Speechbrain Noisy Speech Data Preparation
- Principle:Fastai Fastbook Embedding Analysis
- Principle:Online ml River Prediction Anomaly Detection
- Principle:Confident ai Deepeval OpenAI Agents Instrumentation
- Principle:LaurentMazare Tch rs VarStore Initialization
- Principle:ChenghaoMou Text dedup Union Find
- Principle:Huggingface Transformers Context Parallelism
- Principle:Ray project Ray Cloud Cluster Provisioning
Implementations
- Implementation:FlowiseAI Flowise TagDialog
- Implementation:Webdriverio Webdriverio Options Types
- Implementation:Teamcapybara Capybara Edge Node
- Implementation:Avhz RustQuant BarrierOption
- Implementation:Spotify Luigi CascadingClient
- Implementation:Unslothai Unsloth MoE Ops
- Implementation:Alibaba MNN FlatBuffers IDL Gen General
- Implementation:DistrictDataLabs Yellowbrick ConfusionMatrix Visualizer
- Implementation:Speechbrain Speechbrain Train ESC50 Classification
- Implementation:Huggingface Diffusers ControlNet Img2Img Pipeline
Heuristics
- Heuristic:Mbzuai oryx Awesome LLM Post training Reference Citation Cap 200
- Heuristic:Ggml org Llama cpp Thread Count Tuning
- Heuristic:ChenghaoMou Text dedup False Positive Verification Tradeoff
- Heuristic:Webdriverio Webdriverio Click Interception Workaround
- Heuristic:Cleanlab Cleanlab Confident Threshold Heuristic
- Heuristic:Truera Trulens Rate Limiting And Retry Strategy
- Heuristic:Microsoft LoRA LoRA Init Strategy
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:Facebookresearch Habitat lab DDPPO Straggler Preemption
- Heuristic:Fastai Fastbook Batch Size Selection
Environments
- Environment:Unstructured IO Unstructured Ingest CLI
- Environment:Interpretml Interpret Native Libebm Environment
- Environment:Spotify Luigi AWS S3 Storage
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:Huggingface Datasets TensorFlow Integration
- Environment:NVIDIA NeMo Curator RAPIDS GPU Stack
- Environment:Fastai Fastbook NLP SpaCy Environment
- Environment:Apache Hudi Java Maven Build Environment
- Environment:Datahub project Datahub Python Ingestion
- Environment:Sgl project Sglang Performance Dashboard