Main Page
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:FlagOpen FlagEmbedding Reranker Inference
- Workflow:Tencent Ncnn Vulkan GPU Accelerated Inference
- Workflow:Ggml org Llama cpp OpenAI Compatible Server
- Workflow:ArroyoSystems Arroyo Connection Setup
- Workflow:Google deepmind Dm control MJCF Model Composition
- Workflow:Treeverse LakeFS Garbage Collection
- Workflow:Speechbrain Speechbrain CTC ASR Training
- Workflow:Langgenius Dify Knowledge Base Creation
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:Pytorch Serve Model Deployment
Principles
- Principle:Langgenius Dify URLDrivenState
- Principle:Explodinggradients Ragas Tool Call F1 Evaluation
- Principle:Confident ai Deepeval Assertion Based Evaluation
- Principle:Norrrrrrr lyn WAInjectBench Dynamic Detector Loading Image
- Principle:Apache Paimon Catalog Initialization
- Principle:DevExpress Testcafe Page Object Model
- Principle:Protectai Llm guard Emotion Detection
- Principle:Trailofbits Fickling Pickle Bytecode Parsing
- Principle:Huggingface Optimum Transformation Composition
- Principle:LLMBook zh LLMBook zh github io Deduplication
Implementations
- Implementation:Ollama Ollama Llama Adapter Types
- Implementation:Tencent Ncnn YOLACT Example
- Implementation:Run llama Llama index LabelledRagDataset
- Implementation:Heibaiying BigData Notes Hive Partition and Bucket Config
- Implementation:LMCache LMCache P2PBackend Batched Get Non Blocking
- Implementation:Sgl project Sglang MoE Ops
- Implementation:Kornia Kornia Diamond Square
- Implementation:Apache Shardingsphere StatisticsManager Manage
- Implementation:TA Lib Ta lib python Generate Stream
- Implementation:Rapidsai Cuml Genetic Node
Heuristics
- Heuristic:Lucidrains X transformers Gradient Clipping And Accumulation
- Heuristic:OpenGVLab InternVL Gradient Checkpointing Memory
- Heuristic:Princeton nlp SimPO Left Truncation Strategy
- Heuristic:Mlflow Mlflow Async Logging Best Practices
- Heuristic:MarketSquare Robotframework browser GRPC Response Chunking
- Heuristic:Langfuse Langfuse Ingestion Date Boundary Delay
- Heuristic:Fede1024 Rust rdkafka Cooperative Rebalance Protocol
- Heuristic:Mbzuai oryx Awesome LLM Post training Excel Sheet Name Truncation
- Heuristic:Ggml org Ggml Thread Count Selection
- Heuristic:Risingwavelabs Risingwave Stream Chunk Sizing
Environments
- Environment:ArroyoSystems Arroyo Object Storage
- Environment:Apache Dolphinscheduler Java Runtime
- Environment:FMInference FlexLLMGen CUDA GPU
- Environment:Deepset ai Haystack OpenAI API Environment
- Environment:Datahub project Datahub Spark Lineage Environment
- Environment:Sgl project Sglang Kubernetes
- Environment:Apache Beam Portable Runner Environment
- Environment:Predibase Lorax Docker Container Runtime
- Environment:Eventual Inc Daft Cloud Storage Credentials
- Environment:Scikit learn contrib Imbalanced learn Python Scikit learn