Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4a4f7e6550cf5b327ea0fb241ce7417ab46e1ace' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	CODEOWNERS
#	README.md
#	ci/run.sh
#	docs/development/HOWTO-add-model.md
#	grammars/README.md
#	src/llama-context.cpp
#	src/llama.cpp
#	tools/CMakeLists.txt
#	tools/completion/README.md
#	tools/llama-bench/README.md
This commit is contained in:
Concedo
2025-12-17 14:30:39 +08:00
parent 050a5b1f52 4a4f7e6550
commit c93c4c5505
27 changed files with 1152 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+12 -9
View File
@@ -1096,7 +1096,15 @@ 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) {
@@ -1111,8 +1119,6 @@ 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;
@@ -1151,8 +1157,7 @@ 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;
}
@@ -1184,15 +1189,13 @@ 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;
}