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:Intel Ipex llm LoRA Finetuning
- Workflow:Google deepmind Dm control MJCF Model Composition
- Workflow:Apache Paimon Vector Similarity Search
- Workflow:Apache Hudi Flink Streaming Write
- Workflow:NVIDIA NeMo Aligner DPO Training
- Workflow:Microsoft BIPIA White Box Defense Finetuning
- Workflow:Sail sg LongSpec Speculative Decoding Inference
- Workflow:Langchain ai Langchain Tool Calling Structured Output
- Workflow:Lucidrains X transformers DPO Preference Alignment
- Workflow:Groq Groq python Chat Completion
Principles
- Principle:Explodinggradients Ragas Functional Metric Definition
- Principle:OWASP Www project top 10 for large language model applications Agentic Architecture Mapping
- Principle:Volcengine Verl Prompt Template Design
- Principle:Bitsandbytes foundation Bitsandbytes Global Optimizer Configuration
- Principle:Deepset ai Haystack Document Joining
- Principle:Neuml Txtai Production Deployment
- Principle:ClickHouse ClickHouse Installation
- Principle:Ray project Ray Actor Runtime Initialization
- Principle:CrewAIInc CrewAI Embedding Configuration
- Principle:Huggingface Datasets Streaming Shuffle
Implementations
- Implementation:Kornia Kornia MobileViT
- Implementation:Farama Foundation Gymnasium FrozenLakeEnv
- Implementation:CrewAIInc CrewAI Enterprise API Spec En
- Implementation:SeleniumHQ Selenium Zip
- Implementation:ArroyoSystems Arroyo Checkpoint State
- Implementation:Open compass VLMEvalKit BunnyLLama3
- Implementation:Open compass VLMEvalKit TableVQABench Utils
- Implementation:Farama Foundation Gymnasium HalfCheetahEnv V5
- Implementation:Tensorflow Tfjs Backend Operations Test
- Implementation:Sktime Pytorch forecasting GroupNormalizer
Heuristics
- Heuristic:Infiniflow Ragflow Hybrid Search Fallback Strategy
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
- Heuristic:Apache Kafka Coordinator Loading Commit Interval
- Heuristic:Deepseek ai Janus Bfloat16 Operation Workarounds
- Heuristic:Snorkel team Snorkel DataParallel Default Behavior
- Heuristic:Helicone Helicone Tiered Pricing Threshold Matching
- Heuristic:Romsto Speculative Decoding Shared Tokenizer Requirement
- Heuristic:Datahub project Datahub Warning Deprecated Spark Lineage Legacy
- Heuristic:Mlc ai Mlc llm OpenCL Memory Floor Workaround
- Heuristic:Huggingface Trl DeepSpeed ZeRO3 Generation Tradeoff
Environments
- Environment:Hpcaitech ColossalAI ColossalQA RAG Environment
- Environment:Bigscience workshop Petals Python Hivemind
- Environment:Vespa engine Vespa FNET Transport Config
- Environment:OpenHands OpenHands Integration Credentials
- Environment:Mlfoundations Open flamingo PyTorch CUDA Distributed
- Environment:Unslothai Unsloth CUDA BitsAndBytes
- Environment:Ggml org Llama cpp CMake Build Environment
- Environment:Huggingface Trl Quantization Environment
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:Princeton nlp Tree of thought llm Python OpenAI