llama.cpp/ggml/src/ggml-opencl
lhez 52e5d421f1
opencl: fix rms_norm_mul (#17250)
* opencl: use subgrroup reduce for reduction in rms_norm_mul

* opencl: add comment about workgroup size
2025-11-15 17:40:14 -08:00
..
kernels opencl: fix rms_norm_mul (#17250) 2025-11-15 17:40:14 -08:00
CMakeLists.txt opencl: add kernel to handle mat mul in attention to improve encoding speed (#17181) 2025-11-15 17:33:10 -08:00
ggml-opencl.cpp opencl: fix rms_norm_mul (#17250) 2025-11-15 17:40:14 -08:00