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:Open compass VLMEvalKit Image Benchmark Evaluation
- Workflow:Langgenius Dify Workflow Builder and Execution
- Workflow:Run llama Llama index Embedding Finetuning
- Workflow:Huggingface Peft Prompt Tuning Classification
- Workflow:DistrictDataLabs Yellowbrick Classification Model Evaluation
- Workflow:Huggingface Diffusers Model Quantization
- Workflow:Langfuse Langfuse Prompt management lifecycle
- Workflow:Alibaba ROLL Reward Flow Diffusion Pipeline
- Workflow:Mage ai Mage ai Building a New Source Connector
- Workflow:Speechbrain Speechbrain Whisper ASR Finetuning
Principles
- Principle:Microsoft Onnxruntime Nodejs Inference Execution
- Principle:Sail sg LongSpec Tree Attention Verification
- Principle:Hpcaitech ColossalAI Preference Dataloader Setup
- Principle:Huggingface Diffusers Training Configuration
- Principle:Fastai Fastbook Language Model Fine Tuning
- Principle:Ggml org Llama cpp Prompt Tokenization
- Principle:Haosulab ManiSkill RL Evaluation Checkpointing
- Principle:Teamcapybara Capybara File Uploads
- Principle:DataTalksClub Data engineering zoomcamp Data Deduplication
- Principle:CarperAI Trlx Q Value Guided Generation
Implementations
- Implementation:Microsoft Playwright CssParser
- Implementation:ArroyoSystems Arroyo Plan Graph Builder
- Implementation:Datajuicer Data juicer ExtractEntityAttributeMapper
- Implementation:Ggml org Llama cpp Base64
- Implementation:Ggml org Llama cpp Multimodal Download
- Implementation:OpenGVLab InternVL POPE Benchmark Evaluation
- Implementation:Google deepmind Mujoco Filetype Detection
- Implementation:Duckdb Duckdb CMake Project Configuration
- Implementation:Turboderp org Exllamav2 MMLU Benchmark
- Implementation:PrefectHQ Prefect Prefect Yaml Schema
Heuristics
- Heuristic:Zai org CogVideo Frame Count and Resolution Constraints
- Heuristic:Princeton nlp SimPO Dropout Disabling
- Heuristic:Liu00222 Open Prompt Injection Cosine Similarity Segmentation Threshold
- Heuristic:Heibaiying BigData Notes Kafka Consumer Offset Strategy Tip
- Heuristic:Apache Hudi Write Memory Tuning
- Heuristic:Huggingface Datatrove MinHash Parameter Tuning
- Heuristic:Microsoft DeepSpeedExamples LoRA Learning Rate Scaling
- Heuristic:Vllm project Vllm Attention Backend Selection
- Heuristic:Bigscience workshop Petals Short Inference Pool Merging
- Heuristic:Tencent Ncnn FP16 Precision Selection
Environments
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Lm sys FastChat SFT Training Environment
- Environment:Turboderp org Exllamav2 CUDA GPU Runtime
- Environment:Guardrails ai Guardrails Docker Server Runtime
- Environment:Mlc ai Mlc llm TVM Runtime Environment
- Environment:Guardrails ai Guardrails LLM Provider API Keys
- Environment:Interpretml Interpret Visualization Environment
- Environment:Facebookresearch Habitat lab HITL Runtime Environment