Skip to content

fix(dschat): avoid NaN from masked PPO log-probability padding - #1022

Closed
ot4562-glitch wants to merge 1 commit into
deepspeedai:masterfrom
ot4562-glitch:fix/dschat-ppo-mask-before-exp
Closed

fix(dschat): avoid NaN from masked PPO log-probability padding#1022
ot4562-glitch wants to merge 1 commit into
deepspeedai:masterfrom
ot4562-glitch:fix/dschat-ppo-mask-before-exp

fix(dschat): mask non-finite padding before PPO exponentiation

5fd77ac
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Oct 26, 2026 in 0s

DCO

All commits are signed off!

View more details on DCO