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:EvolvingLMMs Lab Lmms eval End to End Evaluation
- Workflow:Alibaba ROLL Supervised Finetuning Pipeline
- Workflow:Ggml org Llama cpp Speculative Decoding
- Workflow:Deepspeedai DeepSpeed ZeRO Distributed Training
- Workflow:Getgauge Taiko Form Interaction Testing
- Workflow:Lance format Lance Version Management
- Workflow:Microsoft Autogen Multi Agent Conversation
- Workflow:Sgl project Sglang Online Serving With OpenAI API
- Workflow:Risingwavelabs Risingwave Streaming ETL Pipeline
- Workflow:ArroyoSystems Arroyo UDF Development
Principles
- Principle:ArroyoSystems Arroyo Connection Profile Management
- Principle:Run llama Llama index Evaluation Result Analysis
- Principle:Onnx Onnx Model Building
- Principle:Huggingface Optimum Task and Model Resolution
- Principle:DistrictDataLabs Yellowbrick Elbow Method Cluster Selection
- Principle:Huggingface Diffusers DreamBooth Export
- Principle:Huggingface Datasets Progress Reporting
- Principle:Ggml org Llama cpp GGUF Model Loading
- Principle:Spotify Luigi Time Range Scheduling
- Principle:Ray project Ray Object Store Retrieval
Implementations
- Implementation:Pyro ppl Pyro RSA SemanticParsing
- Implementation:Kserve Kserve TrainedModel Reconciler
- Implementation:EvolvingLMMs Lab Lmms eval LongTimeScope Utils
- Implementation:Unslothai Unsloth FastVisionModel From Pretrained
- Implementation:Scikit learn contrib Imbalanced learn BalancedBaggingClassifier
- Implementation:Facebookresearch Audiocraft MAGNeT get pretrained
- Implementation:TobikoData Sqlmesh CroniterCache IncrementalBy
- Implementation:Facebookresearch Audiocraft SampleManager
- Implementation:MarketSquare Robotframework browser Rfbrowser Install
- Implementation:CrewAIInc CrewAI RAG Docs Site Loader
Heuristics
- Heuristic:Intel Ipex llm Llama Padding Token Workaround
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
- Heuristic:VainF Torch Pruning Over Pruning Prevention
- Heuristic:Huggingface Trl Disable Dropout For RL Training
- Heuristic:Allenai Open instruct Polyak Reference Update
- Heuristic:Obss Sahi Match Threshold Tuning
- Heuristic:Neuml Txtai Faiss Index Sizing Tip
- Heuristic:Nautechsystems Nautilus trader Cache Buffer Interval Tuning
- Heuristic:Turboderp org Exllamav2 Dynamic Generator Tuning
- Heuristic:Liu00222 Open Prompt Injection Cosine Similarity Segmentation Threshold
Environments
- Environment:MarketSquare Robotframework browser Node Runtime
- Environment:Ggml org Llama cpp Metal GPU Environment
- Environment:InternLM Lmdeploy Python Dependencies
- Environment:Predibase Lorax Python Server Dependencies
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:SeleniumHQ Selenium Contributor Development Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Requests
- Environment:Haosulab ManiSkill Motion Planning Deps
- Environment:Astronomer Astronomer cosmos Kubernetes Provider
- Environment:Alibaba MNN ARM Mobile Environment