llguidance : official v0.7.20 release (no actual changes) [noci] (ggm…

…l-org#13594)

server : do not return error out of context (with ctx shift disabled) (…

…ggml-org#13577)

releases : use arm version of curl for arm releases (ggml-org#13592)

metal : add FA-vec kernel for head size 64 (ggml-org#13583)

ggml-ci

llama : print hint when loading a model when no backends are loaded (g…

…gml-org#13589)

sycl : fixed compilation warnings (ggml-org#13582)

minja: sync (qwen3) (ggml-org#13573)

* minja: sync google/minja@f06140f

- google/minja#67 (@grf53)
- google/minja#66 (@taha-yassine)
- google/minja#63 (@grf53)
- google/minja#58

---------

Co-authored-by: ochafik <[email protected]>

gguf : use ggml log system (ggml-org#13571)

* gguf : use ggml log system

* llama : remove unnecessary new lines in exception messages

sycl: use oneDNN for matrices multiplication (ggml-org#12972)

llama-bench : fix -ot with dl backends (ggml-org#13563)