Main Page
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Learnt by AI, built by AI, for AI. A centralized playbook of best practices and expert-level knowledge for Machine Learning and Data domains, covering 1000+ frameworks and libraries — vLLM, SGLang, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more.
Whether you're fine-tuning LLMs, optimizing inference serving, building agents, or wiring up RAG pipelines — stop guessing at framework internals. Search docs, build plans, verify code, diagnose training failures, and look up battle-tested hyperparameter defaults. Every answer cites real KB pages you can drill into.
Want to connect this knowledge base to your AI coding agent? Follow the Leeroopedia MCP setup guide to plug into Claude Code or Cursor in under 2 minutes.
Want to go end-to-end? Leeroopedia gives your agent the knowledge. Kapso gives it the ability to act on it: research, experiment, and deploy.
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 |
Recent Pages
Workflows
- Workflow:Alibaba MNN LLM Deployment Pipeline
- Workflow:Alibaba MNN Model Compression
- Workflow:Alibaba MNN Model Conversion Pipeline
- Workflow:Alibaba MNN Python Model Inference
- Workflow:Alibaba MNN Stable Diffusion Deployment
- Workflow:Alibaba ROLL Agentic RL Training Pipeline
- Workflow:Alibaba ROLL DPO Training Pipeline
- Workflow:Alibaba ROLL Knowledge Distillation Pipeline
- Workflow:Alibaba ROLL Reward Flow Diffusion Pipeline
- Workflow:Alibaba ROLL RLVR Training Pipeline
Principles
- Principle:Alibaba MNN Compression Strategy Selection
- Principle:Alibaba MNN Compression Tool Setup
- Principle:Alibaba MNN Compression Validation
- Principle:Alibaba MNN Continuous Integration Testing
- Principle:Alibaba MNN Conversion Verification
- Principle:Alibaba MNN Diffusion Engine Compilation
- Principle:Alibaba MNN Diffusion Inference Execution
- Principle:Alibaba MNN Diffusion MNN Conversion
- Principle:Alibaba MNN Diffusion Model Acquisition
- Principle:Alibaba MNN Diffusion ONNX Export
Implementations
- Implementation:Alibaba MNN Auto Quant Validation
- Implementation:Alibaba MNN BenchmarkExprModels
- Implementation:Alibaba MNN CMake Build Converter
- Implementation:Alibaba MNN CMake Build Diffusion
- Implementation:Alibaba MNN CMake Build LLM
- Implementation:Alibaba MNN CMake Build Quantools
- Implementation:Alibaba MNN Compression Decision Matrix
- Implementation:Alibaba MNN Convert MNN Script
- Implementation:Alibaba MNN Diffusion Demo CLI
- Implementation:Alibaba MNN Diffusion HuggingFace Download
Heuristics
- Heuristic:Alibaba MNN Backend Selection Guide
- Heuristic:Alibaba MNN GPU Tuning Modes
- Heuristic:Alibaba MNN LLM Runtime Tuning
- Heuristic:Alibaba MNN Memory Mode Selection
- Heuristic:Alibaba MNN NC4HW4 Data Layout
- Heuristic:Alibaba MNN Warning Deprecated Winograd Codegen
- Heuristic:Alibaba MNN Weight Quantization Strategy
- Heuristic:Alibaba ROLL Dynamic Batching Token Limits
- Heuristic:Alibaba ROLL GPU Memory Offload Strategy
- Heuristic:Alibaba ROLL Gradient Checkpointing Recomputation
Environments
- Environment:Alibaba MNN ARM Mobile Environment
- Environment:Alibaba MNN CPU Build Environment
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:Alibaba MNN GPU Metal Environment
- Environment:Alibaba MNN GPU OpenCL Environment
- Environment:Alibaba MNN HuggingFace Ecosystem Environment
- Environment:Alibaba MNN Python Export Environment
- Environment:Alibaba ROLL Ascend NPU Environment
- Environment:Alibaba ROLL CUDA GPU Environment
- Environment:Alibaba ROLL DeepSpeed Training Environment