sleepy/llama.cpp
1
0
Fork 0
Code Issues 12 Pull Requests Actions 114 Packages Projects Releases Wiki Activity

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)

Browse Source 
* llama: automatically fit args to free memory

llama-fit-params tool

* fix CI

* hints for bug reports, ensure no reallocation

* fix segfault with Vulkan

* add llama-fit-params to CI

* fix CI

* fix CI

* fix CI

* minor adjustments

* fix assignment of 1 dense layer

* fix logger not being reset on model load failure

* remove --n-gpu-layer hint on model load failure

* fix llama-fit-params verbosity

* fix edge case

* fix typo [no ci]
This commit is contained in:
Johannes Gäßler
2025-12-15 09:24:59 +01:00
committed by GitHub
parent 4aced7a631
commit b1f3a6e5db
26 changed files with 1075 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+12 -9
View File
@@ -1088,7 +1088,15 @@ struct common_init_result::impl {
common_init_result::common_init_result(common_params & params) :
pimpl(new impl{}) {
const auto mparams = common_model_params_to_llama(params);
auto mparams = common_model_params_to_llama(params);
auto cparams = common_context_params_to_llama(params);
if (params.fit_params) {
LOG_INF("%s: fitting params to device memory, to report bugs during this step use -fit off (or --verbose if you can't)\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.verbosity >= 4 ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_ERROR);
}
llama_model * model = llama_model_load_from_file(params.model.path.c_str(), mparams);
if (model == NULL) {
@@ -1103,8 +1111,6 @@ common_init_result::common_init_result(common_params & params) :
// TODO: fix naming
common_init_sampler_from_model(model, params.sampling);
auto cparams = common_context_params_to_llama(params);
if (params.sampling.ignore_eos && llama_vocab_eos(vocab) == LLAMA_TOKEN_NULL) {
LOG_WRN("%s: warning: vocab does not have an EOS token, ignoring --ignore-eos\n", __func__);
params.sampling.ignore_eos = false;
@@ -1143,8 +1149,7 @@ common_init_result::common_init_result(common_params & params) :
llama_context * lctx = llama_init_from_model(model, cparams);
if (lctx == NULL) {
LOG_ERR("%s: failed to create context with model '%s', try reducing --n-gpu-layers if you're running out of VRAM\n",
__func__, params.model.path.c_str());
LOG_ERR("%s: failed to create context with model '%s'\n", __func__, params.model.path.c_str());
return;
}
@@ -1176,15 +1181,13 @@ common_init_result_ptr common_init_from_params(common_params & params) {
llama_model * model = res->model();
if (model == NULL) {
LOG_ERR("%s: failed to load model '%s', try reducing --n-gpu-layers if you're running out of VRAM\n",
__func__, params.model.path.c_str());
LOG_ERR("%s: failed to load model '%s'\n", __func__, params.model.path.c_str());
return res;
}
llama_context * lctx = res->context();
if (lctx == NULL) {
LOG_ERR("%s: failed to create context with model '%s', try reducing --n-gpu-layers if you're running out of VRAM\n",
__func__, params.model.path.c_str());
LOG_ERR("%s: failed to create context with model '%s'\n", __func__, params.model.path.c_str());
return res;
}