ipex-llm icon indicating copy to clipboard operation
ipex-llm copied to clipboard
verified publisher icon intel-analytics

B60 Cannot Use FP16 Precision with GLM4-32B-0414

Open RobinJing opened this issue 7 months ago • 1 comments

Describe the bug B60 Cannot Use FP16 Precision with GLM4-32B-0414 How to reproduce Dtype float32, lowbit fp16, the issue occurs.

Screenshots

Image

RobinJing avatar May 22 '25 09:05 RobinJing

Currently, neither XPU nor CUDA support using float32 dtype when running weight as fp16. .

hzjane avatar May 27 '25 01:05 hzjane