thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama-fit-params: free memory target per device (#18679)

Browse source
This commit is contained in:
Johannes Gäßler 2026-01-08 10:07:58 +01:00 • committed by GitHub
parent 9a5724dee2
commit 64848deb18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 83 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -1097,7 +1097,7 @@ common_init_result::common_init_result(common_params & params) :
if (params.fit_params) {
LOG_INF("%s: fitting params to device memory, for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on\n", __func__);
llama_params_fit(params.model.path.c_str(), &mparams, &cparams,
params.tensor_split, params.tensor_buft_overrides.data(), params.fit_params_target, params.fit_params_min_ctx,
params.tensor_split, params.tensor_buft_overrides.data(), params.fit_params_target.data(), params.fit_params_min_ctx,
params.verbosity >= 4 ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_ERROR);
}