thelittlefireman ad6c66839a ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846) ...

* ggml-cuda: fallback to F32 on device without BF16 hardware acceleration: (Nvidia >= AMPERE, AMD >= RDNA3 or = CDNA)

* apply logic to NVIDIA as well

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

2026-09-14 00:05:10 +02:00

..

cmake

CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)

2026-09-09 12:50:08 +02:00

include

ggml : update ggml_prec specification (#26675)

2026-09-08 09:06:24 +03:00

src

ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846)

2026-09-14 00:05:10 +02:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)

2026-09-09 12:50:08 +02:00