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:Elevenlabs Elevenlabs python Speech to Text Transcription
- Workflow:Huggingface Trl Reward Model Training
- Workflow:Teamcapybara Capybara RSpec Integration Setup
- Workflow:Arize ai Phoenix Span Annotation Pipeline
- Workflow:Turboderp org Exllamav2 EXL2 Model Conversion
- Workflow:FlagOpen FlagEmbedding Reranker Finetuning
- Workflow:InternLM Lmdeploy W4A16 AWQ Quantization
- Workflow:Junyanz Pytorch CycleGAN and pix2pix Pretrained Inference
- Workflow:Vibrantlabsai Ragas Agent Evaluation
- Workflow:Kserve Kserve InferenceGraph Pipeline
Principles
- Principle:Huggingface Open r1 GRPO Training
- Principle:Mlc ai Mlc llm Advanced Serving Features
- Principle:Openai Openai python Image Generation
- Principle:Shiyu coder Kronos Predictor Finetuning
- Principle:Huggingface Datatrove Duplicate Removal
- Principle:Apache Shardingsphere Exclusive Operation Management
- Principle:Mage ai Mage ai SQL Schema Discovery
- Principle:OpenRLHF OpenRLHF PPO Value Loss
- Principle:Getgauge Taiko Specialized Input Controls
- Principle:Googleapis Python genai Content Generation With Cache
Implementations
- Implementation:Openai Openai python Eval Update Params
- Implementation:EvolvingLMMs Lab Lmms eval sglang qwen3vl script
- Implementation:LMCache LMCache SageMaker HyperPod Adapter
- Implementation:Iterative Dvc Repo Data
- Implementation:Kubeflow Pipelines Kubectl Wait Pods
- Implementation:Nightwatchjs Nightwatch Package Lock Manifest
- Implementation:Ray project Ray TaskCaller
- Implementation:FlagOpen FlagEmbedding MLVU Needle Data
- Implementation:CrewAIInc CrewAI Bedrock Browser Session Manager
- Implementation:Haosulab ManiSkill ActorBuilder TableSceneBuilder
Heuristics
- Heuristic:Shiyu coder Kronos Instance Normalization Clipping
- Heuristic:Openai Openai python Retry Backoff Strategy
- Heuristic:MarketSquare Robotframework browser Windows Shell NPM Workaround
- Heuristic:TA Lib Ta lib python Unstable Period Configuration
- Heuristic:Evidentlyai Evidently Column Type Inference Rules
- Heuristic:Facebookresearch Habitat lab DDPPO Straggler Preemption
- Heuristic:Snorkel team Snorkel DataParallel Default Behavior
- Heuristic:Bigscience workshop Petals Short Inference Pool Merging
- Heuristic:Neuml Txtai Memory Streaming Optimization
- Heuristic:Huggingface Datasets Batch Size Optimization
Environments
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:OpenRLHF OpenRLHF Ray Distributed Environment
- Environment:Infiniflow Ragflow Data Source Credentials
- Environment:Huggingface Open r1 vLLM Server
- Environment:Intel Ipex llm RAG LlamaIndex Environment
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Huggingface Trl Quantization Environment
- Environment:Duckdb Duckdb CMake Build Toolchain
- Environment:Ollama Ollama GPU Runtime