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:PrefectHQ Prefect Database Cleanup With Approval
- Workflow:EvolvingLMMs Lab Lmms eval Custom Task Creation
- Workflow:Lm sys FastChat MT Bench Evaluation
- Workflow:Cohere ai Cohere python Semantic Search With Rerank
- Workflow:DevExpress Testcafe CI Integration
- Workflow:Cleanlab Cleanlab Datalab Dataset Audit
- Workflow:Onnx Onnx Reference Evaluation
- Workflow:Confident ai Deepeval Synthetic Dataset Generation
- Workflow:Togethercomputer Together python Embeddings And Reranking
- Workflow:NVIDIA TransformerEngine FSDP Distributed Training
Principles
- Principle:Arize ai Phoenix Prompt Template Rendering
- Principle:Ray project Ray Actor Termination
- Principle:Alibaba MNN Weight Quantization
- Principle:Fede1024 Rust rdkafka Async Message Production
- Principle:LaurentMazare Tch rs Vectorized Environment
- Principle:Getgauge Taiko Browser Closure
- Principle:Ggml org Llama cpp Speculation Strategy Selection
- Principle:Ucbepic Docetl Chunk Result Reduction
- Principle:Ollama Ollama GGUF Model Conversion Qwen3Vl
- Principle:Alibaba MNN Diffusion Inference Execution
Implementations
- Implementation:Huggingface Datatrove NGramDecontamination
- Implementation:Huggingface Datatrove LambdaFilter
- Implementation:Langfuse Langfuse DatasetRunItemUpsertQueue
- Implementation:Anthropics Anthropic sdk python Beta MessageCreateParams
- Implementation:Hpcaitech ColossalAI DetachedReplayBuffer
- Implementation:Openai Openai python Completion Create Params
- Implementation:Apache Paimon CatalogFactory Create for Ray
- Implementation:Lakeraai Pint benchmark Dataset Loading And Formatting
- Implementation:ChenghaoMou Text dedup Save Dataset
- Implementation:Vllm project Vllm LLM Init Speculative
Heuristics
- Heuristic:Mit han lab Llm awq Kernel Selection Thresholds
- Heuristic:Dagster io Dagster Record Over Dataclass
- Heuristic:SeleniumHQ Selenium Cross Binding Consistency Check
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:Deepset ai Haystack BM25 Score Scaling
- Heuristic:Haosulab ManiSkill Initial Pose Performance
- Heuristic:LLMBook zh LLMBook zh github io Deduplication Ngram Threshold
- Heuristic:Online ml River ARF Drift Detection Sensitivity
- Heuristic:Heibaiying BigData Notes Maven Shade Packaging Tip
- Heuristic:Microsoft Semantic kernel Experimental Feature Opt In
Environments
- Environment:MarketSquare Robotframework browser CI GitHub Actions
- Environment:Unslothai Unsloth Llama Cpp
- Environment:Unstructured IO Unstructured All Docs
- Environment:Sgl project Sglang Python Dependencies
- Environment:Truera Trulens Streamlit Dashboard Environment
- Environment:Mistralai Client python GCP Deployment Environment
- Environment:Ray project Ray Java Build Environment
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:FMInference FlexLLMGen NVMe Disk
- Environment:Arize ai Phoenix LLM Provider SDKs