upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-06 18:10:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into backend-sampling

Browse Source
This commit is contained in:
Daniel Bevenius
2025-12-16 09:45:08 +01:00
parent e5737f665f 2aa45ef9e3
commit ad1b60abc4
108 changed files with 5077 additions and 2036 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
common/common.cpp
View File

@@ -1089,7 +1089,15 @@ 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) {
@@ -1104,8 +1112,6 @@ 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;
@@ -1153,8 +1159,7 @@ 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;
}
@@ -1186,15 +1191,13 @@ 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;
}