[Bug] input_type bfloat16 lead to wrong predict results #16698
Labels
needs-triage
PRs or issues that need to be investigated by maintainers to find the right assignees to address it
type: bug
Actual behavior
What actually happened
Environment
Any environment details, such as: Operating System, TVM version, etc
Steps to reproduce
Notice that "float32" can receive a correct inference result.
The text was updated successfully, but these errors were encountered: