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:Wandb Weave SDK Release
- Workflow:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:Princeton nlp SimPO SimPO Training
- Workflow:NVIDIA NeMo Curator Video Curation Pipeline
- Workflow:Hpcaitech ColossalAI Distributed GRPO Training
- Workflow:FlowiseAI Flowise Agentflow V2 Creation
- Workflow:Obss Sahi COCO Evaluation
- Workflow:Ggml org Llama cpp Model Perplexity Evaluation
- Workflow:Openclaw Openclaw Gateway Operations And Diagnostics
- Workflow:NVIDIA NeMo Aligner REINFORCE Training
Principles
- Principle:Eric mitchell Direct preference optimization DPO Loss
- Principle:AUTOMATIC1111 Stable diffusion webui Checkpoint model selection
- Principle:Apache Druid Query History
- Principle:Run llama Llama index Agent Output Processing
- Principle:Alibaba ROLL RLVR Dataset Preparation
- Principle:Scikit learn Scikit learn Pipeline Chaining
- Principle:DistrictDataLabs Yellowbrick Statistical Quartet Visualization
- Principle:Mistralai Client python Training Data Preparation
- Principle:Cohere ai Cohere python Embedding Type Selection
- Principle:Groq Groq python Batch Results Retrieval
Implementations
- Implementation:Infiniflow Ragflow BulkOperateBar Component
- Implementation:Deepspeedai DeepSpeed Py AIO
- Implementation:Farama Foundation Gymnasium Vector Rendering Wrappers
- Implementation:FlowiseAI Flowise GetFileChunks
- Implementation:Heibaiying BigData Notes Flink ListState Usage
- Implementation:Webdriverio Webdriverio XPath PageSource
- Implementation:Intel Ipex llm IpexLLM From Model Id
- Implementation:Langchain ai Langgraph BaseCheckpointSaver Protocol
- Implementation:Lucidrains X transformers NonAutoregressiveWrapper Generate
- Implementation:Online ml River Bandit LinUCBDisjoint
Heuristics
- Heuristic:ArroyoSystems Arroyo Parallelism Configuration
- Heuristic:ChenghaoMou Text dedup Mersenne Prime Backward Compatibility
- Heuristic:Tencent Ncnn Letterbox Vs Direct Resize
- Heuristic:Deepset ai Haystack Pipeline Deep Copy Safety
- Heuristic:Vibrantlabsai Ragas Analytics Silent Failure Pattern
- Heuristic:Romsto Speculative Decoding Shared Tokenizer Requirement
- Heuristic:Bigscience workshop Petals NF4 Quantization Default On CUDA
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:TA Lib Ta lib python NaN Propagation Behavior
- Heuristic:Farama Foundation Gymnasium Sync Vs Async VectorEnv Selection
Environments
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Langchain ai Langgraph Postgres Checkpoint Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:CrewAIInc CrewAI Optional Provider Dependencies
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:MaterializeInc Materialize Docker Compose Runtime
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA
- Environment:Eric mitchell Direct preference optimization PyTorch CUDA
- Environment:Fede1024 Rust rdkafka Kafka Broker Runtime
- Environment:Dagster io Dagster PostgreSQL Storage