b6407

vulkan: support im2col_3d (#15795)

b6405

vulkan: Support pad_ext (#15794)

b6401

kleidiai: generalize compute_forward_kv_cache to compute_forward_fp16…

b6381

CANN: Refactor ND to NZ workspace to be per-device (#15763)

* CANN:Refactor ND to NZ workspace to be per-device in Ascend backend

- Replaced the previous single global ND→NZ workspace with a per-device
  cache using unordered_map keyed by device ID.
- Functions `release_nz_workspace`, `relloc_nz_workspace`, and
  `get_nz_workspace` now manage workspace independently for each device,
  preventing memory conflicts in multi-device / pipeline parallel scenarios.
- This change fixes potential precision issues caused by workspace
  overwrites when multiple devices perform ND→NZ conversions concurrently.

Co-authored-by: hipudding <[email protected]>

* refactor

Signed-off-by: noemotiovon <[email protected]>

* rename

Signed-off-by: noemotiovon <[email protected]>

* fix review comments

Signed-off-by: noemotiovon <[email protected]>

---------

Signed-off-by: noemotiovon <[email protected]>
Co-authored-by: hipudding <[email protected]>

b6373

vulkan: don't use std::string in load_shaders, to improve compile tim…

b6350

vulkan: use memory budget extension to read memory usage (#15545)

* vulkan: use memory budget extension to read memory usage

* fix: formatting and names

* formatting

* fix: detect and cache memory budget extension availability on init

* fix: read `budgetprops.heapBudget` instead of `heap.size` when memory budget extension is available

* style: lints

b6337

server : enable /slots by default and make it secure (#15630)

* server : enable /slots by default and make it secure

ggml-ci

* server : fix tests to pass `--no-slots` when necessary

* server : extend /props with info about enabled endpoints

b6319

server : add documentation for `parallel_tool_calls` param (#15647)

Co-authored-by: Pierre F <[email protected]>

b6314

fix: Compute the full sum in llama-eval-callback, not just the sum of…

b6285

mtmd : support Kimi VL model (#15458)

* convert : fix tensor naming conflict for llama 4 vision

* convert ok

* support kimi vision model

* clean up

* fix style

* fix calc number of output tokens

* refactor resize_position_embeddings

* add test case

* rename build fn

* correct a small bug