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:Dagster io Dagster ETL Pipeline
- Workflow:OpenHands OpenHands Organization Onboarding
- Workflow:Huggingface Alignment handbook Multi Stage Post Training
- Workflow:Triton inference server Server LLM Deployment With TRT LLM
- Workflow:Sail sg LongSpec Speculative Decoding Inference
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:PrefectHQ Prefect API Sourced ETL
- Workflow:Mit han lab Llm awq HuggingFace Model Export
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Apache Spark Kubernetes Deployment
Principles
- Principle:Huggingface Alignment handbook Tokenizer Loading
- Principle:Volcengine Verl Frozen Dataclass Config
- Principle:PeterL1n BackgroundMattingV2 Image sequence writing
- Principle:BerriAI Litellm Cache Initialization
- Principle:AUTOMATIC1111 Stable diffusion webui Frontend Architecture
- Principle:Open compass VLMEvalKit Judge LLM Construction
- Principle:Microsoft Onnxruntime Nodejs Runtime Setup
- Principle:Apache Flink Enriched Row Composition
- Principle:Iamhankai Forest of Thought LLM as Judge
- Principle:Openai Whisper Language Detection
Implementations
- Implementation:Zai org CogVideo Caption Load Video
- Implementation:Langchain ai Langchain Perplexity Types
- Implementation:SeleniumHQ Selenium Closure BrowserEvent
- Implementation:Kornia Kornia Coordinate Grid
- Implementation:Open compass VLMEvalKit Spotting Metric
- Implementation:Mit han lab Llm awq Build vision projector
- Implementation:Haosulab ManiSkill RoboCasaCounter
- Implementation:Speechbrain Speechbrain EncoderClassifier Encode Batch
- Implementation:Testtimescaling Testtimescaling github io Json Dump Shields Badge
- Implementation:FlagOpen FlagEmbedding LLM Embedder LM Model
Heuristics
- Heuristic:Haosulab ManiSkill GPU Memory Buffer Tuning
- Heuristic:Ollama Ollama Sampling Numerical Stability
- Heuristic:Vespa engine Vespa Document Batch Processing Strategy
- Heuristic:Huggingface Trl Distributed Device Map Override
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:VainF Torch Pruning GQA Head Pruning Constraints
- Heuristic:Haosulab ManiSkill Initial Pose Performance
- Heuristic:SeldonIO Seldon core Autoscaling Dual Config Tip
- Heuristic:Bitsandbytes foundation Bitsandbytes CuBLAS Int8 Dimension Alignment
- Heuristic:SeleniumHQ Selenium Bazel Hermetic Build Requirement
Environments
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Sktime Pytorch forecasting Cpflows MQF2 Dependencies
- Environment:Nautechsystems Nautilus trader Arrow Parquet Serialization
- Environment:ArroyoSystems Arroyo Object Storage
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:Vllm project Vllm Buildkite
- Environment:Mistralai Client python Realtime Transcription Environment
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention
- Environment:Heibaiying BigData Notes HBase Environment
- Environment:Neuml Txtai Optional Extras Dependencies