server : disable context shift by default (#15416)

* server : disable context shift by default

ggml-ci

* server : make scopr of test parameters local
This commit is contained in:
Georgi Gerganov 2025-08-19 16:46:37 +03:00 committed by GitHub
parent a6d3cfe7fa
commit d2fcd91cf9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 27 additions and 20 deletions

View file

@ -375,7 +375,7 @@ struct common_params {
bool cont_batching = true; // insert new sequences for decoding on-the-fly
bool flash_attn = false; // flash attention
bool no_perf = false; // disable performance metrics
bool ctx_shift = true; // context shift on inifinite text generation
bool ctx_shift = false; // context shift on inifinite text generation
bool swa_full = false; // use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
bool kv_unified = false; // enable unified KV cache