llama.cpp/ggml-vulkan-shaders.hpp at codeplay/revert-host-alloc

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-07 20:47:30 +02:00

Files

T

0cc4mandslaren ef52d1d16a Update Vulkan RoPE implementation (#7818 )

* Update Vulkan RoPE implementation

* Return nullptr on alloc_buffer when allocation fails, instead of throwing an exception

Minor fixes

* Fix segfault when running out of VRAM

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

---------

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

2024-06-11 21:20:29 +02:00

8.2 MiB

Raw Permalink Blame History

The file is too large to be shown. View Raw

8.2 MiB Raw Permalink Blame History

8.2 MiB

Raw Permalink Blame History