Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com>

(cherry picked from commit 127c52a)

(cherry picked from commit b7a22ba)

…astic (#6802)

Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com>
(cherry picked from commit 86e1d9f)

Co-authored-by: Carlos Mocholi <carlossmocholi@gmail.com>
(cherry picked from commit 01b9cf8)

)

(cherry picked from commit 968ac09)

Co-authored-by: Carlos Mocholi <carlossmocholi@gmail.com>

(cherry picked from commit eb15abc)

(cherry picked from commit 87f0aea)

Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com>

(cherry picked from commit 1c2ecbf)

#6877)

* Ensure we move the model to eval mode before running evaluation

* Ensure we set the flag appropriately across all stages

* Add test, move hooks logic

* Apply same fix to the validate loop

* Update pytorch_lightning/trainer/trainer.py

* Fix function name

* Fix order, add predict

* Shorten the name

* Fix input dm, drop duplicate on predict start hook call, as it's called in the setup function

* Use hook, remove double call

(cherry picked from commit 742c48e)

(cherry picked from commit 90e37ba)

(cherry picked from commit 9c9e2a0)

(cherry picked from commit 5552503)

…6915)

Co-authored-by: Kaushik B <45285388+kaushikb11@users.noreply.github.com>
(cherry picked from commit fe0d088)

* Drop libomp to see what happens

* Drop openmpi/horovod installs

* Revert "Drop libomp to see what happens"

This reverts commit cdd524f

* Update before install

* Skip horovod failing test

(cherry picked from commit e9c3e02)

(cherry picked from commit 23e8dff)

…ightning#6947) (#6958)

Co-Authored-By: Adrian Wälchli <aedu.waelchli@gmail.com>

Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com>

(cherry picked from commit b37b58a)

* update docker base on PT 1.7

* fix path

(cherry picked from commit da1ac3a)

(cherry picked from commit 1b3e4f9)