Jeff Bolz e1f15b454f vulkan: Implement set_tensor_async and the event interfaces (#18047) ...

The goal is to enable the async loading code paths in
llama_model_loader::load_all_data, originally from #7896. This works and the
loads themselves are faster, but with host visible vidmem I think the cost of
allocating/mapping vidmem moves and becomes more expensive, and I don't see a
benefit by default. But with GGML_VK_DISABLE_HOST_VISIBLE_VIDMEM=1 I do see a
significant improvement in model loading time.

2025-12-21 21:52:09 +01:00

..

cmake

ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)

2025-08-07 13:45:41 +02:00

include

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)

2025-12-15 09:24:59 +01:00

src

vulkan: Implement set_tensor_async and the event interfaces (#18047)

2025-12-21 21:52:09 +01:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)

2025-12-19 09:42:28 -08:00