Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Run llama Llama index RAG Query Pipeline
- Workflow:Groq Groq python Streaming Chat Completion
- Workflow:HKUDS AI Trader End to End US Stock Trading
- Workflow:LLMBook zh LLMBook zh github io Data Preprocessing Pipeline
- Workflow:Openai Openai python Embeddings Generation
- Workflow:Neuml Txtai Workflow Orchestration
- Workflow:Huggingface Diffusers Checkpoint Conversion
- Workflow:Facebookresearch Audiocraft EnCodec Compression Training
- Workflow:Unslothai Unsloth QLoRA SFT Finetuning
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
Principles
- Principle:Neuml Txtai Task Wrapping
- Principle:Farama Foundation Gymnasium Q Learning Tabular
- Principle:Fede1024 Rust rdkafka Message Ownership Transfer
- Principle:OWASP Www project top 10 for large language model applications Vulnerability Demonstration with Code Samples
- Principle:Allenai Open instruct Ray Cluster Setup
- Principle:Ggml org Ggml CPU Tensor Operations
- Principle:Ggml org Llama cpp Speculation Strategy Selection
- Principle:Intel Ipex llm KV Cache Eviction
- Principle:OpenRLHF OpenRLHF KL Divergence Estimation
- Principle:Cypress io Cypress DOM Assertion and Interaction
Implementations
- Implementation:Vespa engine Vespa Document ABI Spec
- Implementation:Elevenlabs Elevenlabs python WebhookToolConfigOutput
- Implementation:Run llama Llama index Node Recency Postprocessors
- Implementation:Avhz RustQuant Portfolio
- Implementation:Sktime Pytorch forecasting Base Pkg
- Implementation:Eventual Inc Daft PyO3 Root Module
- Implementation:Huggingface Transformers Update Metadata
- Implementation:Triton inference server Server L0 Trt Dynamic Shape Test
- Implementation:Langfuse Langfuse API Datasets Schema
- Implementation:EvolvingLMMs Lab Lmms eval VATEX Utils
Heuristics
- Heuristic:Microsoft Autogen Parallel Tool Call Safety
- Heuristic:Datajuicer Data juicer Checkpoint Resumption Strategy
- Heuristic:Iamhankai Forest of Thought Tree Iteration Scaling
- Heuristic:Apache Druid Cluster Health Diagnostic Thresholds
- Heuristic:Apache Flink Hadoop Thread Safety Mutexes
- Heuristic:Openai CLIP Class Name Curation
- Heuristic:Microsoft Agent framework Declaration Only Tools Pattern
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
- Heuristic:Diagram of thought Diagram of thought Strict Vs Flexible Critic Rigor
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
Environments
- Environment:Nightwatchjs Nightwatch BrowserStack Cloud
- Environment:Speechbrain Speechbrain HuggingFace Transformers
- Environment:Protectai Modelscan H5py Optional
- Environment:Microsoft DeepSpeedExamples VisualChat Training Environment
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Nightwatchjs Nightwatch Selenium WebDriver 4
- Environment:Mlfoundations Open flamingo PyTorch CUDA Distributed
- Environment:Haosulab ManiSkill GPU CUDA Simulation
- Environment:DataTalksClub Data engineering zoomcamp Kafka Confluent Environment
- Environment:Wandb Weave Trace Server Infrastructure