merge_qkv: add command loine argument to enable

2026-04-22 15:39:23 +00:00 · 2025-10-29 13:27:55 +02:00
parent ca5cff8677
commit 4e8f371e76
8 changed files with 23 additions and 9 deletions
--- a/include/llama.h
+++ b/include/llama.h
@@ -382,6 +382,7 @@ extern "C" {
        bool repack_tensors;// repack if available
        bool use_thp;       // use transparent huge pages (linux only)
        bool validate_quants; // if true, check for NaNs while loading the model
+        bool merge_qkv;     // if true, merge separate Q, K, V tensors into a single, contiguous tensor
    };

    // NOTE: changing the default values of parameters marked as [EXPERIMENTAL] may cause crashes or incorrect results in certain configurations