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:FMInference FlexLLMGen HELM Benchmark Evaluation
- Workflow:Groq Groq python Streaming Chat Completion
- Workflow:Fastai Fastbook Image Classification
- Workflow:Kserve Kserve Multi Model Serving
- Workflow:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:Huggingface Datasets Dataset Preprocessing
- Workflow:Langfuse Langfuse Evaluation pipeline
- Workflow:PacktPublishing LLM Engineers Handbook Model Evaluation
- Workflow:Nautechsystems Nautilus trader Strategy development
- Workflow:Roboflow Rf detr Custom Dataset Finetuning
Principles
- Principle:Infiniflow Ragflow Citation Insertion
- Principle:Togethercomputer Together python Result Integration
- Principle:Open compass VLMEvalKit Results Summarization
- Principle:Openai Openai agents python Guardrail Execution
- Principle:Fastai Fastbook Classifier Data Preparation
- Principle:Apache Druid Query Composition
- Principle:Huggingface Trl DPO Training
- Principle:Ggml org Llama cpp Target Model Loading
- Principle:Deepspeedai DeepSpeed Supervised Fine Tuning
- Principle:CARLA simulator Carla Playback Speed Control
Implementations
- Implementation:Dotnet Machinelearning FactorizationMachineCore
- Implementation:Openai Openai python Realtime Server Events
- Implementation:Scikit learn Scikit learn Bunch
- Implementation:Huggingface Datasets Dataset To Parquet
- Implementation:Ollama Ollama ConvertModel
- Implementation:Elevenlabs Elevenlabs python ForcedAlignmentClient
- Implementation:Googleapis Python genai Sphinx BaseStemmer
- Implementation:Romsto Speculative Decoding AutoModelForCausalLM From Pretrained
- Implementation:NVIDIA TransformerEngine Normalization C API
- Implementation:FMInference FlexLLMGen DeepSpeed Op Builder
Heuristics
- Heuristic:LMCache LMCache Prefix Based Retrieval Pattern
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Deepset ai Haystack BM25 Score Scaling
- Heuristic:Huggingface Peft Gradient Checkpointing With Quantization
- Heuristic:Datahub project Datahub Docker Memory Preflight
- Heuristic:Apache Flink False Positive Availability Optimization
- Heuristic:Openclaw Openclaw WebSocket Reconnection And Session Cleanup
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Facebookresearch Audiocraft FSDP Distributed Training Tips
- Heuristic:Isaac sim IsaacGymEnvs DR Setup Only Flag
Environments
- Environment:Ucbepic Docetl Docker Deployment
- Environment:Farama Foundation Gymnasium MuJoCo Physics Backend
- Environment:Vibrantlabsai Ragas Python 3 9 Core Environment
- Environment:Dotnet Machinelearning ONNX Runtime Environment
- Environment:Microsoft Semantic kernel OpenAI API Environment
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:BerriAI Litellm Provider API Credentials
- Environment:Openai Whisper Numba
- Environment:Heibaiying BigData Notes Java 8 Maven Environment
- Environment:Sgl project Sglang Web