Hugging Face Forums
CPU/Memory Utilization Too High When Running Inference on Falcon 40B Instruct
Amazon SageMaker
cvetanovskaa
June 26, 2023, 2:38pm
2
Hi
@philschmid
do you happen to have any ideas what might be going on?
show post in topic
Related topics
Topic
Replies
Views
Activity
Sagemaker Serverless Inference
Amazon SageMaker
22
8999
May 22, 2024
Fail predict using Falcon-7B-Instruct
🤗Transformers
0
658
June 1, 2023
Deploy falcon 7b problems
Beginners
4
2782
June 6, 2023
Getting error in the inference stage of Transformers Model (Hugging Face)
🤗Transformers
0
782
October 11, 2022
CUDA error for inference on GPU instance
Amazon SageMaker
2
761
May 16, 2023