(Bugfix, ggml-cuda) Pool alloc count fix + small size computation type adjustment (#18559)

* CUDA: Fixed obj byte size instead of obj count being passed to pool alloc (fattn-common, dst_tmp_meta) * CUDA: Explicitly casted some of the int alloc counts before multiplication in argsort --------- Co-authored-by: pl752 <maximpl752@gmail.com>
2026-01-03 11:13:40 +01:00
parent bcfc8c3cec
commit 9dba9f5352
2 changed files with 3 additions and 3 deletions
@@ -918,7 +918,7 @@ void launch_fattn(
        blocks_num.y = 1;
        blocks_num.z = 1;

-        dst_tmp_meta.alloc(blocks_num.x*ncols * (2*2 + DV) * sizeof(float));
+        dst_tmp_meta.alloc(((size_t) blocks_num.x) * ncols * (2 + DV/2));
    } else {
        const int ntiles_KQ = (K->ne[1] + nbatch_fa - 1) / nbatch_fa; // Max. number of parallel blocks limited by tensor size.