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:Ggml org Llama cpp Model Quantization
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:OpenGVLab InternVL Multi Stage Pretraining
- Workflow:Protectai Modelscan Custom Scanner Plugin
- Workflow:Apache Paimon Data Ingestion With Ray Sink
- Workflow:Huggingface Open r1 Model Evaluation
- Workflow:Heibaiying BigData Notes Kafka Producer Consumer Pipeline
- Workflow:Pyro ppl Pyro Discrete Enumeration
- Workflow:Openai Openai python Fine Tuning Job Management
- Workflow:Spcl Graph of thoughts Custom GoT Use Case Integration
Principles
- Principle:Mlfoundations Open flamingo Vision Conditioned Text Generation
- Principle:Tensorflow Tfjs Activation Functions
- Principle:Apache Airflow DAG File Discovery
- Principle:Ggml org Llama cpp Performance
- Principle:FMInference FlexLLMGen Distributed Pipeline Parallel Inference
- Principle:EvolvingLMMs Lab Lmms eval Parallel Inference
- Principle:PeterL1n BackgroundMattingV2 Dataset composition
- Principle:OpenBMB UltraFeedback Model Sampling
- Principle:Groq Groq python Binary Response Handling
- Principle:Pyro ppl Pyro JIT Compilation
Implementations
- Implementation:Mlc ai Mlc llm MLCEngineBase Init
- Implementation:MarketSquare Robotframework browser Go To Click Fill Text
- Implementation:Ucbepic Docetl JoinOptimizer
- Implementation:PacktPublishing LLM Engineers Handbook HuggingFaceProcessor Run
- Implementation:DataTalksClub Data engineering zoomcamp Redpanda CSV Consumer
- Implementation:Apache Druid Query Context Completions
- Implementation:Duckdb Duckdb PCG Random
- Implementation:Mistralai Client python GCP Models Init
- Implementation:Anthropics Anthropic sdk python Thinking Stream Events
- Implementation:Pytorch Serve Inferentia2 OPT Handler
Heuristics
- Heuristic:Turboderp org Exllamav2 Quantization Conversion Tips
- Heuristic:Norrrrrrr lyn WAInjectBench NaN Inf Fallback FP32 Recovery
- Heuristic:Neuml Txtai Llama Cpp Context Fallback
- Heuristic:Datahub project Datahub Warning Deprecated Spark Lineage Legacy
- Heuristic:Ray project Ray Autoscaling Delay Tuning
- Heuristic:Kserve Kserve VLLM GPU Memory Utilization
- Heuristic:Truera Trulens Trace Compression Token Limits
- Heuristic:Huggingface Datatrove MinHash Parameter Tuning
- Heuristic:Iamhankai Forest of Thought Self Correction Confidence Threshold
- Heuristic:Microsoft DeepSpeedExamples SuperOffload NUMA Binding
Environments
- Environment:Zai org CogVideo Diffusers Finetuning Environment
- Environment:Apache Druid Web Console Development
- Environment:Tencent Ncnn Vulkan Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Cypress io Cypress Browser Requirements
- Environment:Spotify Luigi Hadoop HDFS Cluster
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:Ucbepic Docetl Python Runtime
- Environment:Apache Shardingsphere Calcite Federation Engine
- Environment:FMInference FlexLLMGen CUDA GPU