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:Openai CLIP Zero shot image classification
- Workflow:Huggingface Peft LoRA Embedding Semantic Search
- Workflow:Duckdb Duckdb Building From Source
- Workflow:Marker Inc Korea AutoRAG RAG Pipeline Optimization
- Workflow:OpenHands OpenHands GitHub Webhook Event Processing
- Workflow:Microsoft Semantic kernel Plugin Integration And Function Calling
- Workflow:Romsto Speculative Decoding Speculative Decoding Inference
- Workflow:Vibrantlabsai Ragas Experiment Driven Development
- Workflow:Vibrantlabsai Ragas RAG Evaluation
- Workflow:Huggingface Datatrove Dataset Tokenization
Principles
- Principle:NVIDIA DALI Spatial Augmentation Detection
- Principle:ClickHouse ClickHouse Server Startup For Testing
- Principle:Cypress io Cypress Configuration Validation
- Principle:Langchain ai Langgraph Runtime Config Access
- Principle:Tensorflow Serving Performance Monitoring
- Principle:Datajuicer Data juicer Operator Package Registration
- Principle:Apache Spark Release Environment Isolation
- Principle:Marker Inc Korea AutoRAG Corpus Sampling
- Principle:Trailofbits Fickling Pickle Payload Injection
- Principle:Ggml org Llama cpp Merged Model Quantization
Implementations
- Implementation:Treeverse LakeFS Java SDK Model ObjectError
- Implementation:Intel Ipex llm AutoModelForCausalLM From Pretrained DPO
- Implementation:Microsoft Autogen Studio Render Message
- Implementation:Vllm project Vllm Marlin MoE Generate Kernels
- Implementation:Huggingface Transformers LoraConfig
- Implementation:Scikit learn contrib Imbalanced learn NeighbourhoodCleaningRule
- Implementation:Google deepmind Mujoco Engine Sleep
- Implementation:Datahub project Datahub DataHubClientV2 Close
- Implementation:CARLA simulator Carla Python Actor Bindings
- Implementation:Treeverse LakeFS Java SDK JSON
Heuristics
- Heuristic:Danijar Dreamerv3 Adaptive Gradient Clipping
- Heuristic:Astronomer Astronomer cosmos Memory Optimised Imports
- Heuristic:Apache Spark K8s Container Patterns
- Heuristic:Speechbrain Speechbrain Score Normalization Tips
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Ggml org Llama cpp Context Size Alignment
- Heuristic:Langgenius Dify API Token Single Flight Caching
- Heuristic:Togethercomputer Together python Repetition Penalty Conflict
- Heuristic:Tencent Ncnn Vulkan Pipeline Warmup
- Heuristic:Alibaba ROLL PPO Clipping Defaults
Environments
- Environment:Apache Airflow Database Backend Environment
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:Shiyu coder Kronos HuggingFace Hub Access
- Environment:Alibaba MNN GPU OpenCL Environment
- Environment:Webdriverio Webdriverio Cloud Service Credentials
- Environment:Microsoft Autogen Extension Optional Dependencies
- Environment:Pytorch Serve vLLM Engine Environment
- Environment:Lakeraai Pint benchmark Python 310 With Transformers
- Environment:Mlfoundations Open flamingo PyTorch CUDA Distributed
- Environment:MaterializeInc Materialize Kubernetes Helm Runtime