whisper.cpp/ggml
Jeff Bolz 04d0f9a066
vulkan: Reuse conversion results in prealloc_y (llama/15410)
* vulkan: Reuse conversion results in prealloc_y

Cache the pipeline and tensor that were most recently used to fill prealloc_y,
and skip the conversion if the current pipeline/tensor match.

* don't use shared pointer for prealloc_y_last_pipeline_used
2025-09-20 13:42:38 +03:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (llama/15094) 2025-08-18 20:30:45 +03:00
include musa: add GGML_UNUSED_VARS (llama/15446) 2025-09-20 13:42:38 +03:00
src vulkan: Reuse conversion results in prealloc_y (llama/15410) 2025-09-20 13:42:38 +03:00
.gitignore
CMakeLists.txt CUDA: replace GGML_CUDA_F16 with CUDA arch checks (llama/15433) 2025-09-20 13:42:38 +03:00