b4967

SYCL: implement memset ggml backend buffer interface (#12580)

* SYCL: implement memset ggml backend buffer interface

* use GGML_ABORT macro

* Do not wait for all queues to finish for memset operation

b4966

HIP: Add support for RDNA4 targets (#12372)

b4964

upgrade to llguidance 0.7.10 (#12576)

b4963

clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA…

b4961

ggml : fix MUL_MAT_ID repack with Q8_K (#12544)

* ggml : fix MUL_MAT_ID repack with Q8_K

ggml-ci

* ggml : improve repack templates

ggml-ci

b4958

run: de-duplicate fmt and format functions and optimize (#11596)

b4957

ggml-cpu : update KleidiAI to v1.5.0 (#12568)

ggml-cpu : bug fix related to KleidiAI LHS packing

Signed-off-by: Dan Johansson <[email protected]>

b4956

SYCL: disable Q4_0 reorder optimization (#12560)

ggml-ci

b4953

context : fix worst-case reserve outputs (#12545)

ggml-ci

b4951

opencl: simplify kernel embedding logic in cmakefile (#12503)

Co-authored-by: Max Krasnyansky <[email protected]>