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.
This commit is contained in:
Daniel Han authored and GitHub committed 2026-11-21 12:10:38 +01:00
1 parent 838d942438
commit 690b87d881
4 files changed
+7

No files matched your search

+1
View File
@@ -2019,6 +2019,7 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) {
output_in_s = create_tensor(tn(LLM_TENSOR_OUTPUT, "input_scale"), {1}, TENSOR_NOT_REQUIRED);
}
}
post_arch_tensors(ml);
}
ml.done_getting_tensors();