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:BerriAI Litellm Response Caching
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:Alibaba MNN Model Conversion Pipeline
- Workflow:Googleapis Python genai Image Generation Pipeline
- Workflow:Getgauge Taiko Gauge Integration Testing
- Workflow:Apache Flink File Source Pipeline
- Workflow:CarperAI Trlx SFT Instruction Tuning
- Workflow:Tensorflow Serving Batched Inference Pipeline
- Workflow:Marker Inc Korea AutoRAG Evaluation Data Creation
- Workflow:Zai org CogVideo Diffusers Text to Video Inference
Principles
- Principle:Helicone Helicone Dashboard Visualization
- Principle:Getgauge Taiko Browser Closure
- Principle:Bentoml BentoML Model Cleanup
- Principle:Huggingface Datatrove Word Level Statistics
- Principle:Confident ai Deepeval Synthetic Data Synthesis
- Principle:AUTOMATIC1111 Stable diffusion webui Memory Management
- Principle:Webdriverio Webdriverio Step Definition Binding
- Principle:Treeverse LakeFS S3 Data Writing
- Principle:Vllm project Vllm Draft Model Acquisition
- Principle:Sdv dev SDV Single Table Quality Evaluation
Implementations
- Implementation:Apache Paimon Schema With Blob Options
- Implementation:Ggml org Ggml Sycl softmax
- Implementation:Run llama Llama index RankGPTRerank
- Implementation:OpenHands OpenHands GithubManager Send Message
- Implementation:DistrictDataLabs Yellowbrick InterclusterDistance Visualizer
- Implementation:Online ml River Base Ensemble
- Implementation:Haosulab ManiSkill UnitreeH1WithHands
- Implementation:Dotnet Machinelearning FastTree SurplusMART Derivatives
- Implementation:Langgenius Dify InputVar Types
- Implementation:Shiyu coder Kronos Config Init
Heuristics
- Heuristic:Pytorch Serve Ampere Tensor Core Optimization
- Heuristic:Shiyu coder Kronos Learning Rate And Optimizer Tuning
- Heuristic:Puppeteer Puppeteer Navigation Race Condition Avoidance
- Heuristic:Axolotl ai cloud Axolotl Memory Optimization Tips
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:Open compass VLMEvalKit SKIP ERR For Graceful Inference
- Heuristic:Alibaba ROLL KL Coefficient Tuning
- Heuristic:Heibaiying BigData Notes HBase Connection Thread Safety Tip
- Heuristic:Pola rs Polars Avoid Lambda In Aggregation
- Heuristic:Interpretml Interpret EBM Hyperparameter Tuning Guide
Environments
- Environment:Turboderp org Exllamav2 Build Toolchain
- Environment:Getgauge Taiko Linux System Libraries
- Environment:Pyro ppl Pyro CUDA GPU Acceleration
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:CarperAI Trlx DeepSpeed Multi GPU
- Environment:Wandb Weave Python SDK Runtime
- Environment:Evidentlyai Evidently Python Core Environment
- Environment:Tencent Ncnn Build Environment
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Haotian liu LLaVA Python CUDA Training Environment