b4174

vulkan: Fix a vulkan-shaders-gen arugment parsing error (#10484)

The vulkan-shaders-gen was not parsing the --no-clean argument correctly.
Because the previous code was parsing the arguments which have a value only
and the --no-clean argument does not have a value, it was not being parsed
correctly. This commit can now correctly parse arguments that don't have values.

b4173

Introduce llama-run (#10291)

It's like simple-chat but it uses smart pointers to avoid manual
memory cleanups. Less memory leaks in the code now. Avoid printing
multiple dots. Split code into smaller functions. Uses no exception
handling.

Signed-off-by: Eric Curtin <[email protected]>

b4171

server : add more information about error (#10455)

b4170

server : enable cache_prompt by default (#10501)

ggml-ci

b4169

metal : enable mat-vec kernels for bs <= 4 (#10491)

b4168

Rename Olmo1124 to Olmo2 (#10500)

b4167

llama : accept a list of devices to use to offload a model (#10497)

* llama : accept a list of devices to use to offload a model

* accept `--dev none` to completely disable offloading

* fix dev list with dl backends

* rename env parameter to LLAMA_ARG_DEVICE for consistency

b4164

server : add speculative decoding support (#10455)

* server : add speculative decoding support

ggml-ci

* server : add helper function slot.can_speculate()

ggml-ci

b4163

ggml : add support for dynamic loading of backends (#10469)

* ggml : add support for dynamic loading of backends

---------

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

b4162

tests : fix compile warning