whisper.cpp/ggml
Johannes Gäßler e35d1375ee
HIP: use v_dot2_f32_f16 instruction for FA (llama/15884)
2025-09-20 13:42:52 +03:00
..
cmake
include cuda : fix supports_op condition for get_rows when number of blocks is too large (llama/15868) 2025-09-20 13:42:52 +03:00
src HIP: use v_dot2_f32_f16 instruction for FA (llama/15884) 2025-09-20 13:42:52 +03:00
.gitignore
CMakeLists.txt ggml-cpu: drop support for nnpa intrinsics (llama/15821) 2025-09-20 13:42:50 +03:00