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:Facebookresearch Habitat lab PointNav PPO Training
- Workflow:LaurentMazare Tch rs Transfer Learning
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:Mit han lab Llm awq HuggingFace Model Export
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
- Workflow:Ggml org Ggml Model Conversion And Quantization
- Workflow:Mistralai Client python OCR Document Processing
- Workflow:Mage ai Mage ai API Source Extraction
- Workflow:Snorkel team Snorkel Data Augmentation
- Workflow:Mit han lab Llm awq AWQ Model Quantization
Principles
- Principle:EvolvingLMMs Lab Lmms eval Task Utility Functions
- Principle:Arize ai Phoenix Prompt Versioning
- Principle:Ggml org Llama cpp Target Model Loading
- Principle:FMInference FlexLLMGen Distributed Checkpoint Management
- Principle:Alibaba ROLL LLM Response Generation
- Principle:Mlflow Mlflow Evaluation Dataset Preparation
- Principle:TA Lib Ta lib python Abstract Function Execution
- Principle:Neuml Txtai Retrieval Augmented Generation
- Principle:InternLM Lmdeploy SmoothQuant Quantization
- Principle:SeleniumHQ Selenium WebDriver Session For CDP
Implementations
- Implementation:Hiyouga LLaMA Factory PPO Trainer
- Implementation:Onnx Onnx Domain Constants
- Implementation:Huggingface Trl Get Dataset DataCollatorForPreference DPO
- Implementation:Tensorflow Serving Static Storage Path Source
- Implementation:Mbzuai oryx Awesome LLM Post training Abstract Review Categorization
- Implementation:Eric mitchell Direct preference optimization Concatenated Forward
- Implementation:Google deepmind Mujoco MJWarp Collision Primitive
- Implementation:Open compass VLMEvalKit ShortQA Utils
- Implementation:CARLA simulator Carla ServerSideSensor
- Implementation:Facebookresearch Habitat lab HumanoidPickPolicy
Heuristics
- Heuristic:Princeton nlp Tree of thought llm API Request Batching
- Heuristic:Iamhankai Forest of Thought UCB Exploration Constant
- Heuristic:ChenghaoMou Text dedup Bloom Filter Single Process
- Heuristic:EvolvingLMMs Lab Lmms eval Limit Flag Testing Only
- Heuristic:Unslothai Unsloth Merge Memory Management
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:OpenBMB UltraFeedback Principle Distribution Tuning
- Heuristic:Lucidrains X transformers Rotary Position Embedding Selection
- Heuristic:Pytorch Serve Torch Compile Best Practices
- Heuristic:Facebookresearch Audiocraft Chroma Conditioning Cache Requirement
Environments
- Environment:Huggingface Datatrove Slurm Cluster Environment
- Environment:Promptfoo Promptfoo Python Runtime
- Environment:Apache Shardingsphere Calcite Federation Engine
- Environment:LMCache LMCache NIXL Transfer Library
- Environment:Elevenlabs Elevenlabs python FFmpeg Mpv
- Environment:LMCache LMCache Python Runtime
- Environment:Openai Openai agents python LiteLLM Dependencies
- Environment:EvolvingLMMs Lab Lmms eval Python Runtime Environment
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:Neuml Txtai GPU Accelerator Environment