happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml
History
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
…
include
…
src vulkan: Implement set_tensor_async and the event interfaces (#18047) 2025-12-21 21:52:09 +01:00
.gitignore
…
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