Aman GuptaandAman Gupta ea07c5d3b7 ggml-cuda: fix blackwell native builds (llama/18361) ...

* ggml-cuda: fix blackwell native builds

Replace 12x in native architectures by 12xa

* replace for GGML_NATIVE=OFF too

* only replace for native

* remove 120f-virtual for default compilation

---------

Co-authored-by: Aman Gupta <aman>

2025-12-31 17:52:09 +02:00

..

cmake

…

include

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (llama/16653)

2025-12-18 08:20:56 +02:00

src

ggml-cuda: fix blackwell native builds (llama/18361)

2025-12-31 17:52:09 +02:00

.gitignore

…

CMakeLists.txt

ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (llama/17977)

2025-12-31 17:52:09 +02:00