Files
llama.cpp/ggml/src/ggml-opencl/kernels
rmatif 912ff8c119 OpenCL: add initial FA support (#14987)
* add F16/F16 fa support

* fix kernel init

* use mad instead of fma

* use inline function

* mark FA with sinks as unsupported for now

* add pragma unroll to loops
2025-08-16 01:05:55 -07:00
..
2025-07-21 10:03:19 -07:00
2025-07-04 23:24:56 -07:00
2025-07-09 18:16:12 +02:00