hexagon: accept the zeroed rope probe in supports_op ( #28995 ) llama probes weight placement with a rope where all params are 0, so rejecting n_dims == 0 or freq_base == 0 puts rope_freqs on the CPU. That splits the decode graph at every full-attention layer (gemma-4-E2B: 5…
Read the original source — github.com
release · Shared by tscosj
0 comments
No comments yet.