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:Liu00222 Open Prompt Injection DataSentinel Detection
- Workflow:NVIDIA DALI Image Preprocessing Pipeline
- Workflow:Sgl project Sglang Online Serving With OpenAI API
- Workflow:Risingwavelabs Risingwave Docker Deployment
- Workflow:FlowiseAI Flowise Chatbot Deployment
- Workflow:Ggml org Llama cpp Model Quantization
- Workflow:PrefectHQ Prefect Dbt Model Orchestration
- Workflow:Intel Ipex llm vLLM Serving
- Workflow:Triton inference server Server Model Performance Tuning
- Workflow:Recommenders team Recommenders Neural Collaborative Filtering
Principles
- Principle:Getgauge Taiko Element Assertion
- Principle:Ggml org Llama cpp Android Integration
- Principle:CrewAIInc CrewAI Tool Design
- Principle:Getgauge Taiko Dropdown Selection
- Principle:Datahub project Datahub Entity Upsert
- Principle:Tensorflow Serving Servable Caching
- Principle:Webdriverio Webdriverio Source Analysis
- Principle:Deepspeedai DeepSpeed Pipeline Evaluation
- Principle:Ggml org Llama cpp LoRA Adapter Acquisition
- Principle:Huggingface Trl GRPO Training Loop
Implementations
- Implementation:NVIDIA NeMo Curator Base Downloader
- Implementation:Getgauge Taiko Core Utilities
- Implementation:Deepset ai Haystack ChatPromptBuilder
- Implementation:Explodinggradients Ragas MetricBasePrompt Class
- Implementation:Hpcaitech ColossalAI ExperienceMaker Base
- Implementation:OpenBMB UltraFeedback Model Pool Sampling
- Implementation:Ollama Ollama Convert Mistral Causal
- Implementation:Intel Ipex llm NPU Model Convert
- Implementation:Online ml River Bandit LinUCBDisjoint
- Implementation:Google deepmind Mujoco mjv makeScene
Heuristics
- Heuristic:Mlc ai Mlc llm Metal KV Cache Capacity Limit
- Heuristic:Huggingface Diffusers Dtype Precision Selection
- Heuristic:Truera Trulens Temperature Zero For Deterministic Scoring
- Heuristic:Alibaba MNN Backend Selection Guide
- Heuristic:Allenai Open instruct Logprob Clamping
- Heuristic:Hiyouga LLaMA Factory CUDA Memory Optimization
- Heuristic:OpenHands OpenHands Redis Distributed Locking
- Heuristic:Confident ai Deepeval Async Concurrency Tuning
- Heuristic:Kserve Kserve NCCL RoCE Auto Detection
- Heuristic:Apache Kafka Log4j Migration Compatibility
Environments
- Environment:Trailofbits Fickling Python Runtime
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Sgl project Sglang Distributed
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Huggingface Diffusers Training Environment
- Environment:Huggingface Transformers BitsAndBytes Quantization Env
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Vllm project Vllm Intel XPU
- Environment:Norrrrrrr lyn WAInjectBench Conda Python 39 CUDA Environment
- Environment:Shiyu coder Kronos Comet ML Logging