Nicolò Scipione 4737a8c780 sycl: Add reorder to Q6_K mmvq implementation (llama/13885) ...

* Add Reorder to Q6_K mmvq implementation

* Address PR comments: clean up comments

* Remove unused parameter after refactoring q4_k

* Adding inline to function and removing unnecessary reference to int

---------

Signed-off-by: nscipione <nicolo.scipione@codeplay.com>

2025-06-10 12:40:33 +03:00

..

cmake

cmake: Factor out CPU architecture detection (llama/13883)

2025-06-01 15:14:44 +03:00

include

threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (llama/12995)

2025-06-01 15:14:44 +03:00

src

sycl: Add reorder to Q6_K mmvq implementation (llama/13885)

2025-06-10 12:40:33 +03:00

.gitignore

…

CMakeLists.txt

llama : allow using mmap without PrefetchVirtualMemory, apply GGML_WIN_VER to llama.cpp sources (llama/14013)

2025-06-10 12:40:33 +03:00