b5054

sync: minja (#12739)

* sync: minja

https://github.com/google/minja/pull/57

* fix json include

b5053

kv-cache : simplify + fix warning for recurrent models (#12756)

ggml-ci

b5052

ci: add Linux cross-compile build (#12428)

b5050

gguf-split : --merge now respects --dry-run option (#12681)

* gguf-split now respects dry-run option

* removing trailing space

b5049

sycl: allow ggml-sycl configuration and compilation using Visual Stud…

b5046

vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency (…

b5045

vulkan: set cmake minimum and project name in vulkan-shaders (#12744)

b5043

CUDA: Prefer vector flash decoding kernel for Gemma models (#12738)

* Prefer vector flash decoding kernel for Gemma models

Vector flash decoding kernel was not being picked for models with head dimension 256. Gemma models are in this category.
Removing this limit improves e2e performance by upto 12% in gen phase throughput for Gemm models.

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

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

---------

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

b5041

vulkan: Fix missing cmake logic for dot product extension (#12721)

b5039

sync : minja (inclusionAI/Ling) and update tests (#12699)

Signed-off-by: Xiaodong Ye <[email protected]>