]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml: don't include arm_neon.h when using CUDA 12 with ARM Neon (ggml/1187)
authorcmdr2 <redacted>
Thu, 10 Apr 2025 12:23:08 +0000 (17:53 +0530)
committerGeorgi Gerganov <redacted>
Thu, 10 Apr 2025 21:17:47 +0000 (00:17 +0300)
commitcb79c2e7fa28e874694c14598c1fd2fde82263e1
treede788b2db7be9abe348b255fd03570d079a3d965
parentfe92821ea9ae53f3088cf2699a9e102448295fa0
ggml: don't include arm_neon.h when using CUDA 12 with ARM Neon (ggml/1187)

fix #1186
ggml/src/ggml-impl.h