Main Page: Difference between revisions
Remove __NOCACHE__ text, use PHP hook instead |
Update: add SuperML plugin and Leeroopedia MCP links |
||
| Line 32: | Line 32: | ||
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. | 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 | '''Connect your AI coding agent.''' Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously: | ||
''' | * [https://github.com/Leeroo-AI/superml '''SuperML plugin'''] — full-stack AI/ML coding agent | ||
* [https://github.com/Leeroo-AI/leeroopedia-mcp '''Leeroopedia MCP'''] — knowledge search for any coding agent | |||
== Browse by Category == | == Browse by Category == | ||
Revision as of 11:42, 14 March 2026
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 — full-stack AI/ML coding agent
- Leeroopedia MCP — knowledge search for any coding agent
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:Dagster io Dagster DSPy Optimization
- Workflow:Roboflow Rf detr ONNX Export
- Workflow:Huggingface Peft DreamBooth LoRA Diffusion
- Workflow:Cohere ai Cohere python Semantic Search With Rerank
- Workflow:Unstructured IO Unstructured Chunking And Embedding
- Workflow:Pytorch Serve Large Model Inference
- Workflow:Scikit learn contrib Imbalanced learn Imbalanced Model Evaluation
- Workflow:Cypress io Cypress CI Pipeline Integration
- Workflow:VainF Torch Pruning Object Detection Pruning
- Workflow:Intel Ipex llm QLoRA Finetuning
Principles
- Principle:Arize ai Phoenix Annotation Querying
- Principle:Romsto Speculative Decoding Logits Processing
- Principle:Bentoml BentoML Model Persistence
- Principle:Huggingface Transformers Inference Measurement
- Principle:Puppeteer Puppeteer Device Emulation
- Principle:Langfuse Langfuse Dataset Item Processing
- Principle:Mlflow Mlflow Trace Destination Configuration
- Principle:Helicone Helicone Platform Statistics
- Principle:EvolvingLMMs Lab Lmms eval YAML Task Configuration
- Principle:Cypress io Cypress Headless Test Execution
Implementations
- Implementation:Triton inference server Server L0 Trt Dynamic Shape Test
- Implementation:FlowiseAI Flowise ArrayRenderer
- Implementation:Apache Airflow BaseTracer Protocol
- Implementation:Marker Inc Korea AutoRAG Factoid Query Gen
- Implementation:Ollama Ollama KVCache Interface
- Implementation:Mage ai Mage ai Knowi Client
- Implementation:Hpcaitech ColossalAI Cpp Extension
- Implementation:Microsoft Agent framework Agent Async Context Manager
- Implementation:Risingwavelabs Risingwave DatetimeTypeConverter
- Implementation:Togethercomputer Together python Batches Create Batch
Heuristics
- Heuristic:ARISE Initiative Robomimic Video Recording Optimization
- Heuristic:Spcl Graph of thoughts GoT Decompose Sort Merge Strategy
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
- Heuristic:Risingwavelabs Risingwave Memory Cache Eviction Policy
- Heuristic:Scikit learn Scikit learn Feature Scaling Numerical Stability
- Heuristic:Huggingface Alignment handbook Gradient Checkpointing Use Cache
- Heuristic:ARISE Initiative Robosuite Domain Randomization Tuning
- Heuristic:Princeton nlp SimPO Multi Seed Diversity
- Heuristic:Langgenius Dify API Token Single Flight Caching
- Heuristic:Rapidsai Cuml Float64 Kernel Stability
Environments
- Environment:Duckdb Duckdb Release Publishing Env
- Environment:Evidentlyai Evidently Python Core Environment
- Environment:Mlc ai Mlc llm Python Serving Environment
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Protectai Llm guard API Server Deployment
- Environment:Speechbrain Speechbrain Speech Enhancement Dependencies
- Environment:Microsoft Semantic kernel DotNet SDK Environment
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:Roboflow Rf detr Python GPU Environment
- Environment:ThreeSR Awesome Inference Time Scaling Semantic Scholar API Environment