talk-llama : sync llama.cpp (#3084)

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-04-28 16:40:23 +03:00
committed by GitHub
parent 28dcdff4c5
commit f3c42399a3
36 changed files with 16940 additions and 12400 deletions

View File

@ -29,6 +29,7 @@ struct llama_cparams {
bool offload_kqv;
bool flash_attn;
bool no_perf;
bool warmup;
enum llama_pooling_type pooling_type;