sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests 1 Actions 175 Packages Projects Releases Wiki Activity

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
6 changed files with 83 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/fit-params/fit-params.cpp
+1 -1
View File
@@ -27,7 +27,7 @@ int main(int argc, char ** argv) {
auto mparams = common_model_params_to_llama(params);
auto cparams = common_context_params_to_llama(params);
const llama_params_fit_status status = 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);
if (status != LLAMA_PARAMS_FIT_STATUS_SUCCESS) {
LOG_ERR("%s: failed to fit CLI arguments to free memory, exiting...\n", __func__);