KV Cache defrag hash overflow - TMP Fix by @slaren

#6685
ggerganov · Apr 16, 2024 · eedd42e · eedd42e
1 parent 8a56075
commit eedd42e
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/llama.cpp b/llama.cpp
@@ -10702,7 +10702,7 @@ static void llama_kv_cache_defrag_internal(struct llama_context & lctx) {
     // each move requires 6*n_layer tensors (see build_defrag)
     //   - source view, destination view, copy operation
     //   - x2 for keys and values
-    const uint32_t max_moves = LLAMA_MAX_NODES/(6*n_layer);
+    const uint32_t max_moves = (LLAMA_MAX_NODES - 2*n_layer)/(6*n_layer);
 
     // determine which KV cells to move where
     //