metal : enable FA for MLA heads (#18950)

This commit is contained in:
Georgi Gerganov
2026-01-20 12:21:28 +02:00
committed by GitHub
parent 7dee9ff59a
commit 271191906c
3 changed files with 11 additions and 12 deletions
+2 -6
View File
@@ -1078,12 +1078,8 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
op->src[0]->ne[0] != 112 &&
op->src[0]->ne[0] != 128 &&
op->src[0]->ne[0] != 192 &&
op->src[0]->ne[0] != 256) {
return false;
}
if (op->src[0]->ne[0] == 576) {
// DeepSeek sizes
// TODO: disabled for now, until optmized
op->src[0]->ne[0] != 256 &&
op->src[0]->ne[0] != 576) {
return false;
}
if (op->src[1]->type != op->src[2]->type) {