You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As discussed in the recent PR #4193 , it would be good to extend the utility function for converting float32 to bfloat16 to support different modes (e.g., truncation vs rounding; the treatment of NaN could potentially lead to distinguishing pure-truncation vs. truncation with correct NaN handling).
The text was updated successfully, but these errors were encountered:
Feature Request
As discussed in the recent PR #4193 , it would be good to extend the utility function for converting float32 to bfloat16 to support different modes (e.g., truncation vs rounding; the treatment of NaN could potentially lead to distinguishing pure-truncation vs. truncation with correct NaN handling).
The text was updated successfully, but these errors were encountered: