ci: fix cross-compile sync issues (ggml-org#12804)

convert : ability to lazy-load safetensors remotely without downloadi…

…ng to disk (ggml-org#12820)

* gguf util : add SafetensorRemote

* fix style

* convert: add --remote option

* convert : allow using lazy remote tensors

It's a bit slow for now since everything is blocking and single-threaded.

* correct metadata.name

* small style fix

* support HF_TOKEN

* convert : use writeable buffer for remote lazy tensors

* convert : fix flake8 lint regarding lamdba assigment

* multithreaded download

* multithread: print debug

* fix style

* Revert "multithreaded download"

This reverts commit 42fc895.

* bring back _get_request_headers

---------

Co-authored-by: Francis Couture-Harpin <[email protected]>

opencl : fix memory allocation size (ggml-org#12649)

issue:
#17 (comment)

This patch fixes the memory allocation size
not exceeding the maximum size of the OpenCL device.

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

* SYCL: implement memset ggml backend buffer interface

* use GGML_ABORT macro

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

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

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

vulkan: Add N/2 and N/4 optimized paths in coopmat2 shader (ggml-org#…

…12312)

llguidance build fixes for Windows (ggml-org#11664)

* setup windows linking for llguidance; thanks @phil-scott-78

* add build instructions for windows and update script link

* change VS Community link from DE to EN

* whitespace fix

cuda : add ampere to the list of default architectures (ggml-org#11870)

Make logging more verbose (ggml-org#11714)

Debugged an issue with a user who was on a read-only filesystem.

Signed-off-by: Eric Curtin <[email protected]>

vulkan: optimize coopmat2 iq2/iq3 callbacks (ggml-org#11521)

* vulkan: optimize coopmat2 iq2/iq3 callbacks

* build: trigger CI on GLSL compute shader changes