Spaces:
No application file
No application file
Troubleshooting Hugging Face Inference Latency on Intel Evo i7 with Hugging Face Transformers Version 4.22: Any Insights?
#15
by jonathanjone - opened
Hi everyone,
I’m currently working with Hugging Face Transformers version 4.22 on my Intel Evo i7 laptop, and I’m experiencing some noticeable latency issues during inference. The models are running slower than expected, despite the intel evo i7 specs seeming more than capable for the task.
Has anyone here faced similar performance challenges when running Hugging Face Transformers version 4.22 on an Intel Evo i7? Any tips on troubleshooting latency or optimizing performance? I’ve tried adjusting a few settings, but I’d really appreciate any suggestions from the community, especially if anyone has found solutions for improving inference speed.
Looking forward to your insights!