search

quic / ai-hub-models

The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
https://aihub.qualcomm.com
BSD 3-Clause "New" or "Revised" License
438 stars 60 forks source link

error occured when run llama_v2_7b_chat_quantized_PromptProcessor_3_Quantized #84

Closed yolanda1224git closed 1 month ago

yolanda1224git commented 1 month ago

Describe the issue I run llama_v2_7B model in AI-HUB, and llama_v2_7b_chat_quantized_PromptProcessor_3_Quantized reports an error, the reason is "Job timed out after 8h". inference job is https://app.aihub.qualcomm.com/jobs/jmg9o0jmg/ profiling job is https://app.aihub.qualcomm.com/jobs/jz5wyw24g/.

Other 3 parts run successfully. Only the 3th one run failed. Could you help to checkout the reason please?

bhushan23 commented 1 month ago

Hi @yolanda1224git both of the jobs are timed out. It's mostly due to large wait time when job was submitted.

Could you please resubmit these jobs? you can use qai-hub APIs to get the model and dataset to avoid model re-upload as follows 

>>> import qai_hub as hub
>>> job = hub.get_job('jmg9o0jmg')
>>> hub.submit_inference_job(job.model, inputs=job.inputs, device=job.device)

similarly, you can submit profile job with given options. Please feel free to re-open issue if error persists