llama.cpp/ggml
Jeff Bolz f549b0007d
vulkan: Call ggml_vk_buffer_write_2d from ggml_vk_buffer_copy (#16793)
This lets the copy to the destination device use the host-visible
vidmem optimization.
2025-10-29 09:53:04 +01:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) 2025-10-22 13:47:09 -07:00
src vulkan: Call ggml_vk_buffer_write_2d from ggml_vk_buffer_copy (#16793) 2025-10-29 09:53:04 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) 2025-10-22 13:47:09 -07:00