llama.cpp
690b87d8 - model : inkling2_loop share the loop slots after the scale pass (#32704)

Commit
1 day ago
model : inkling2_loop share the loop slots after the scale pass (#32704) The loop slots copied the physical layers at the end of load_arch_tensors, before the generic pass attaches the optional .scale tensors, so the later passes through the core ran NVFP4 experts without their per-expert scales. Add an optional post_arch_tensors hook that runs after the scale pass and share the slots there.
Author
Parents
Loading