thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

llama-fit-params: keep explicit --ctx-size 0 (#19070)

Browse source
This commit is contained in:
Johannes Gäßler 2026-01-24 22:13:08 +01:00 • committed by GitHub
parent 4e5b83b226
commit e9fd8dcab4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 12 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/llama.cpp
View file

@ -311,8 +311,12 @@ static void llama_params_fit_impl(
__func__, hp_nct, cparams->n_ctx, memory_reduction/MiB);
}
} else {
LLAMA_LOG_INFO("%s: default model context size is %" PRIu32 " which is <= the min. context size of %" PRIu32 " -> no change\n",
__func__, hp_nct, n_ctx_min);
if (n_ctx_min == UINT32_MAX) {
LLAMA_LOG_INFO("%s: user has requested full context size of %" PRIu32 " -> no change\n", __func__, hp_nct);
} else {
LLAMA_LOG_INFO("%s: default model context size is %" PRIu32 " which is <= the min. context size of %" PRIu32 " -> no change\n",
__func__, hp_nct, n_ctx_min);
}
}
} else {
LLAMA_LOG_INFO("%s: context size set by user to %" PRIu32 " -> no change\n", __func__, cparams->n_ctx);