Commit 68353db3 authored by Thomas Joerg's avatar Thomas Joerg Committed by TensorFlower Gardener
Browse files

[XLA:GPU] Ignore fp precision for multi-output fusion. 

This allows fusing producers with fp16 outputs into reduce fusions which are always fp32.

PiperOrigin-RevId: 205224989
parent dbf10397
Show whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please to comment