metal: fix NaN in mul_mm_id when activations exceed f16 range ( #26223 ) test-backend-ops: reproduce MUL_MAT_ID NaN for activations beyond f16 The Metal mul_mm_id path narrows src1 to half for the simdgroup MMA ( S1 = half in every instantiation; ggml-metal.metal:10582 and…
Read the original source — github.com
release · Shared by tscosj
0 comments
No comments yet.