Kawrakow 51eea5715f Better PP performance with split mode "graph" and 3+ GPUs (#1069) ...

* This should do the trick for PP

* Command line option to set max. extra VRAM that the scheduler can use

* Fix bug and cleanup

* Looks like with this change it is working with tensor overrides

* Nah, it is not working

* OK, this seems to be working

* Disable split scheduling with tensor overrides

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-12-17 07:40:25 +01:00

..

llama.h

Better PP performance with split mode "graph" and 3+ GPUs (#1069)

2025-12-17 07:40:25 +01:00