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.

b4863

`server`: extract <think> tags from qwq outputs (#12297)

* extract <think> tags from qwq outputs

* const for all static regexes in chat.cpp

b4862

`tool-call`: ensure there's always a non-empty tool call id (#12292)

b4859

llava : fix bug in minicpm-v code (#11513)

* fix bug in minicpm-v code

* update readme of minicpm-v

b4858

server : add speculative decoding presets for FIM (#12287)

b4856

ggml-backend : make path_str compatible with C++20 (#12269)