metal : add FA kernels for HSK=96, HSV=64 (MiniCPM3) ( #28599 ) metal : add FA kernels for HSK=96, HSV=64 (MiniCPM3) MiniCPM3 sets attention.key_length to 96 and does not set attention.value_length, which defaults to n_embd / n_head = 64. Metal had no (96, 64) instantiation, so…
Read the original source — github.com
release · Shared by tscosj
0 comments
No comments yet.