b4067

vulkan: Throttle the number of shader compiles during the build step.…

b4066

metal : more precise Q*K in FA vec kernel (#10247)

b4065

server : enable KV cache defrag by default (#10233)

ggml-ci

b4062

vulkan: Fix newly added tests for permuted mul_mat and 1D im2col (#10…

b4061

metal : reorder write loop in mul mat kernel + style (#10231)

* metal : reorder write loop

* metal : int -> short, style

ggml-ci

b4060

metal : fix build and some more comments (#10229)

b4059

metal : fix F32 accumulation in FA vec kernel (#10232)

b4058

llama : fix Qwen model type strings

b4057

metal : hide debug messages from normal log

b4056

ggml: fix zero division in ‘dne’ calculation in CUDA COUNT_EQUAL oper…