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:Onnx Onnx Model Composition
- Workflow:Mlflow Mlflow LLM Tracing
- Workflow:NVIDIA TransformerEngine Comm GEMM Overlap Training
- Workflow:Gretelai Gretel synthetics DGAN Timeseries Generation
- Workflow:Langchain ai Langchain Tool Calling Structured Output
- Workflow:Openai Whisper Word Level Timestamps
- Workflow:Romsto Speculative Decoding Speculative Decoding Inference
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:Scikit learn contrib Imbalanced learn Imbalanced Model Evaluation
- Workflow:Explodinggradients Ragas Agent Evaluation
Principles
- Principle:FlowiseAI Flowise Workspace Navigation
- Principle:PrefectHQ Prefect Batched Flow Run Deletion
- Principle:Wandb Weave Pre release Validation
- Principle:Open compass VLMEvalKit MCQ Prompt Construction
- Principle:Infiniflow Ragflow Knowledge Base Selection
- Principle:Ollama Ollama Model Architecture Support
- Principle:FlagOpen FlagEmbedding Finetuned Reranker Validation
- Principle:Princeton nlp Tree of thought llm Experiment Configuration
- Principle:Langfuse Langfuse Prompt Cache Invalidation
- Principle:LaurentMazare Tch rs Tensor Format Conversion
Implementations
- Implementation:Treeverse LakeFS Java SDK Model Setup
- Implementation:Bentoml BentoML Cloud Login
- Implementation:Ray project Ray ParallelActor ActorCall
- Implementation:Tencent Ncnn Ncnnmerge
- Implementation:FMInference FlexLLMGen Get Opt Config
- Implementation:ChenghaoMou Text dedup Save Dataset
- Implementation:Sgl project Sglang CPU Torch Extension
- Implementation:Microsoft Semantic kernel InvokePromptStreamingAsync
- Implementation:Iterative Dvc Repo Init
- Implementation:Microsoft Playwright APIResponse Methods
Heuristics
- Heuristic:Huggingface Datasets Parquet Shard Sizing
- Heuristic:Unstructured IO Unstructured PDF Element Sorting
- Heuristic:Bitsandbytes foundation Bitsandbytes Compressed Statistics Double Quantization
- Heuristic:Pyro ppl Pyro MCMC Warmup Adaptation
- Heuristic:Evidentlyai Evidently Drift Detection Thresholds
- Heuristic:Microsoft Semantic kernel Experimental Feature Opt In
- Heuristic:DevExpress Testcafe MacOS Browser Launch Serialization
- Heuristic:Vespa engine Vespa RPM Zstd Compression Settings
- Heuristic:Online ml River SNARIMAX Default Regressor Pipeline
- Heuristic:Unslothai Unsloth GGUF Quantization Selection
Environments
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:Hpcaitech ColossalAI CUDA GPU Environment
- Environment:BerriAI Litellm Observability Stack
- Environment:Allenai Open instruct CUDA GPU Training
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Farama Foundation Gymnasium MuJoCo Physics Backend
- Environment:Anthropics Anthropic sdk python GCP Vertex Environment
- Environment:MarketSquare Robotframework browser Docker Container