llama.cpp/ggml
Jeff Bolz 74d4f5b041
vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency (#12630)
There seems to be a bubble waking up from waitForFences, which costs a few
percent performance and also increased variance in performance. This change
inserts an "almost_ready" fence when the graph is about 80% complete and we
waitForFences for the almost_ready fence and then spin (with _mm_pauses) waiting
for the final fence to be signaled.
2025-04-04 07:54:35 +02:00
..
cmake scripts : update sync + fix cmake merge 2025-03-27 10:09:29 +02:00
include metal : improve FA + improve MoE (#12612) 2025-03-28 20:21:59 +02:00
src vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency (#12630) 2025-04-04 07:54:35 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : add logging for native build options/vars (whisper/2935) 2025-03-30 08:33:31 +03:00