b6684

metal : fix loop bound in ggml_mem_ranges (#16412)

b6683

llama : fix shapes for bert/mpt q/k norm (#16409)

b6682

ggml : fix graph reallocation with multiple chunks (#16396)

reallocation is needed if a single chunk grows in size,
even if total allocation size stays the same or is lower

b6681

Fix missing messages on sibling navigation (#16408)

* fix: resolve message disappearing issue when navigating between regenerated siblings by using current leaf nodes instead of cached sibling IDs

* chore: update webui build output

* chore: update webui build output

b6679

vulkan: Fix FA coopmat1 invalid array indexing (#16365)

When computing sinks, the cm1 shader was looping r from 0 to Br rather than
to rows_per_thread. I must have copied this from the scalar path (where it is
correct), and somehow it wasn't causing failures on current drivers.

b6678

ci : change macos-13 to macos-15-intel (#16401)

This commit updates the macos-13 runners to macos-15-intel.

The motivation for this changes is the macos-13 runners are scheduled
to be retired on 2025-12-04.

Refs: https://github.blog/changelog/2025-09-19-github-actions-macos-13-runner-image-is-closing-down/

b6676

vulkan: in flash attention, bounds check against nem1 (don't rely on …

b6673

test-barrier : do not use more threads than physically available (#16…

b6672

ggml webgpu: add support for soft_max, optimize rms_norm (#16357)

* Add inplace softmax

* Move rms_norm to split row approach

* Update debug for supports_op

* clean up debug statements

* Update tests/test-backend-ops.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

---------

Co-authored-by: Georgi Gerganov <[email protected]>

b6671

model : Apertus model implementation (#15852)

* First attempt

* No permute during convert (fixes qk tensors), proper norm application.

* RoPE = NeoX

* Coherence!

* Migrate xielu params from tensors to hyperparameters

* Simple CUDA kernel

* Revert stupid LLM refactorings

* Chat template support

* configchecker / flake8 errors

* Reorder unary.cu

* I do conclude that LLMs are, in fact, stupid.

* Fix after merge

* Final newline

* Make xIELU an UNARY_OP

* Final newline

* Correctly account for parameter shift

* Argh.

* Update ggml/src/ggml-cpu/unary-ops.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

* Refactor: remove unused methods, inline and factorize softplus, add const modifiers

* Revert CUDA changes, implement xIELU as a separate OP

* Pesky newline

* Add float2half / half2float for F16 inputs/outputs

* CUDA variants, attempt 2

* Actually, attempt 3

* Update ggml/src/ggml-cuda/unary.cu

Co-authored-by: Johannes Gäßler <[email protected]>

* Missing convert header

* Proper formula and reference for xIELU in the comments.

* Modify unary-ops.cpp to add the functor-based logic besides the template system to retain optimizations

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <[email protected]>

* Add tensor mappings for Apertus to global list instead

* Fix lazy on scalars

* Update ggml/src/ggml-cuda/unary.cu

Co-authored-by: Johannes Gäßler <[email protected]>

* Add comment about the constraints on positive/negative alpha

* Change `softplus` to `ggml_softplus`

---------

Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: Johannes Gäßler <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>