b5935

parallel : add option for different RNG seeds (#14757)

ggml-ci

b5787

Add Conv2d for CPU (#14388)

* Conv2D: Add CPU version

* Half decent

* Tiled approach for F32

* remove file

* Fix tests

* Support F16 operations

* add assert about size

* Review: further formatting fixes, add assert and use CPU version of fp32->fp16

b5538

cmake: Guard GGML_CPU_ALL_VARIANTS by architecture (#13890)

b5516

opencl: add new ops - `argsort`, `div`, `sub`, `addrows`, `sigmoid`, …

b5350

mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj (#13459)

b5307

docker : disable arm64 and intel images (#13356)

b5219

llama : llm_type order by size (#13177)

b5195

common : add common_remote_get_content (#13123)

* common : add common_remote_get_content

* support max size and timeout

* add tests

b5171

rpc : add command line option for number of threads for the CPU backe…

b5145

opencl: fix incorrect local_size index in profiling log (#12868)