b6323

vulkan: Skip syncing for prealloc_y when it is reused (#15544)

b6294

tests : fix test-opt with GGML_BACKEND_DL (#15599)

b6275

vulkan: fix min subgroup 16 condition for mmid subgroup optimization …

b6264

vulkan: apply MUL_MAT_ID subgroup optimization to non-coopmat devices…

b6239

llama : remove deprecated llama_kv_self API (#15472)

ggml-ci

b6209

opencl: mark `argsort` unsupported if cols exceed workgroup limit (#1…

b6190

vulkan: disable spirv-opt for bfloat16 shaders (#15352)

b6178

common : fix double bos, use common_chat_templates for add_bos and ad…

b6123

cuda: refactored ssm_scan and use CUB (#13291)

* cuda: refactored ssm_scan to use CUB

* fixed compilation error when when not using CUB

* assign L to constant and use size_t instead of int

* deduplicated functions

* change min blocks per mp to 1

* Use cub load and store warp transpose

* suppress clang warning

b6121

gguf-py : add Numpy MXFP4 de/quantization support (#15111)

* gguf-py : add MXFP4 de/quantization support

* ggml-quants : handle zero amax for MXFP4