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:Groq Groq python Audio Transcription
- Workflow:Datajuicer Data juicer Text Data Processing Pipeline
- Workflow:Neuml Txtai Agent Execution
- Workflow:Neuml Txtai Workflow Orchestration
- Workflow:Obss Sahi COCO Evaluation
- Workflow:CarperAI Trlx PPO Sentiment Training
- Workflow:Alibaba MNN Python Model Inference
- Workflow:Lance format Lance Vector Search Pipeline
- Workflow:OpenGVLab InternVL LoRA Finetuning
- Workflow:Rapidsai Cuml GPU Clustering
Principles
- Principle:Huggingface Diffusers Prompt Encoding
- Principle:Helicone Helicone Provider Dashboard Integration
- Principle:Eventual Inc Daft Data Materialization
- Principle:Hiyouga LLaMA Factory Direct Preference Optimization
- Principle:Mistralai Client python GCP Chat And FIM
- Principle:EvolvingLMMs Lab Lmms eval MCP Tool Integration
- Principle:Langgenius Dify Role Based Access Control
- Principle:Huggingface Trl DPO Reference Model Setup
- Principle:Spcl Graph of thoughts Thought Aggregation
- Principle:TobikoData Sqlmesh Data Exploration And Validation
Implementations
- Implementation:Open compass VLMEvalKit Aria
- Implementation:MaterializeInc Materialize Platform Check Subclasses
- Implementation:Hiyouga LLaMA Factory V1 Rendering Plugin
- Implementation:BerriAI Litellm PostHog Logger
- Implementation:Langgenius Dify UseExplore
- Implementation:Apache Hudi HoodieFlinkCompactor Main
- Implementation:Microsoft Playwright UtilityScriptSerializers
- Implementation:Tensorflow Serving source router h
- Implementation:Vespa engine Vespa SimpleTokenizer Tokenize
- Implementation:Vllm project Vllm CPU Attn AMX
Heuristics
- Heuristic:Hiyouga LLaMA Factory Mixed Precision Training Tips
- Heuristic:Lance format Lance Vector Index Tuning
- Heuristic:Huggingface Peft DoRA Inference Caching
- Heuristic:Pyro ppl Pyro MCMC Warmup Adaptation
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Huggingface Diffusers LoRA Safe Fusing
- Heuristic:Microsoft Autogen Graph Validation Rules
- Heuristic:OpenHands OpenHands Fail Open Rate Limiting
- Heuristic:OpenBMB UltraFeedback Score 10 Anomaly Correction
- Heuristic:Apache Airflow Task Dependency Isolation
Environments
- Environment:DevExpress Testcafe Docker Xvfb Container
- Environment:Ggml org Ggml C Cpp Build Environment
- Environment:Fede1024 Rust rdkafka Kafka Broker Runtime
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:SqueezeAILab ETS Multi GPU Sglang Runtime
- Environment:Mlc ai Web llm Node Build Toolchain
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Openai Evals Optional Provider APIs
- Environment:HKUDS AI Trader API Credentials
- Environment:Scikit learn contrib Imbalanced learn Python Scikit learn