b4874

vulkan: fix bug in coopmat1 mul_mat_id (#12316)

* tests: run mul_mat_id with a larger N

* vulkan: fix bug in coopmat1 mul_mat_id

b4873

CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows …

b4872

ggml-backend : fix backend search path (#12330)

* Fix backend search path

* replace .native() with '/'

* reverted .native()

b4871

metal : Cache the Metal library at the device context level (#12265)

b4870

clip : bring back GPU support (#12322)

* clip : bring back GPU support

* use n_gpu_layers param

* fix double free

* ggml_backend_init_by_type

* clean up

b4869

mat vec double buffer (#12188)

b4868

musa: support new arch mp_31 and update doc (#12296)

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

b4867

opencl: use OpenCL C standard supported by the device (#12221)

This patch nudges the llama.cpp a bit to be supported on PoCL which
doesn't support OpenCL C CL2.0. The issue is solved by querying the
device for the supported OpenCL C versions and using the highest one
available.

b4865

tests : fix test-quantize-fns to init the CPU backend (#12306)

ggml-ci

b4864

common : refactor '-o' option (#12278)

As discussed in PR 'llama-tts : add -o option' (#12042):

* common_params : 'out_file' string is the only output file name parameter left in common_params. It's intended to be used in all example programs implementing an '-o' option.

* cvector-generator, export-lora, imatrix : default output filenames moved from 'common_params' to the 'main()' of each example program.