ik_llama_opt/ggml
Kawrakow 8f7bd74afb Revert "Fix race in the CUDA DeepSeek FA kernel (#406)"
This reverts commit 36e6e888b75ae93fb5aac212bb0e147d8379ae23.
I should have tested. We get NaNs.
2025-05-11 12:22:19 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Add copyright notices (#317) 2025-04-07 10:43:26 +02:00
src Revert "Fix race in the CUDA DeepSeek FA kernel (#406)" 2025-05-11 12:22:19 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Compile time option to use bf16 for qunts without MMQ kernels (#261) 2025-03-18 07:37:10 +01:00