sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-13 04:24:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

KV Cache defrag hash overflow - TMP Fix by @slaren

Browse Source 
#6685
This commit is contained in:
Pierrick HYMBERT
2024-04-16 10:24:34 +02:00
parent 8a56075b07
commit eedd42e376
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@@ -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
//