Here lists the common issues that developers encounter when using the GAI toolkit. 
- [LLaMA.2-1B] [PTQ] ValueError: Mismatched Input Dimensions When Running llama3.2-1B Calibration Script
- [LLaMA3-8B] [PTQ] Common Issues in Calibration Dataset Generation
- [LLaMA3-8B] [Pre-inference Setup] Missing llama3_8b.tiktoken in TokenizerPath
- [DeepSeek] [On-device Inference] Runtime Error: Cache Type Size Mismatch
- [GAI SD v2.1 + ControlNet] [Inference Setup] NDK-build Compilation Failure Before Model Inference
- [LLM + Tree Speculative Decoding] [Inference Setup] Unable to Locate modelOutputQuantScale
- [LLaVA-1.5-7B] [PTQ] Script Error During Calibration
- [Qwen2.5-0.5B] [DLA Compilation] Floating point exception (core dumped) when running compile_generative.sh
- [Qwen2.5-0.5B] [On-device Inference] Incorrect Output (Hallucination) During DLA Inference
- [Qwen2.5-3B] [On-device Inference] Input Mismatch and Output Repetition
- [Qwen2.5-7B] [On-device Inference] Repetitive Output Content for Inference
- [Qwen2.5-7B] Error in PTQ calibration, occured “ImportError: cannot import name VideoInput” when running “bash 1_make_ptq_calibration_dataset.sh”