talk-llama : sync llama.cpp

ggml-ci
2025-08-09 01:24:37 +02:00 · 2025-05-13 13:20:19 +03:00
parent a14c89aefa
commit f890560575
25 changed files with 2847 additions and 1125 deletions
--- a/examples/talk-llama/llama-cparams.h
+++ b/examples/talk-llama/llama-cparams.h
@ -30,6 +30,7 @@ struct llama_cparams {
    bool flash_attn;
    bool no_perf;
    bool warmup;
+    bool op_offload;

    enum llama_pooling_type pooling_type;