public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-21 01:31:53 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-05-25 12:26:07 +03:00
parent 0a62a579cc
commit 865ec171aa
129 changed files with 1593 additions and 395 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-model-loader.cpp
+10 -3
View File
@@ -1312,9 +1312,16 @@ struct ggml_tensor * llama_model_loader::create_tensor_as_view(struct ggml_conte
return tensor;
}
void llama_model_loader::done_getting_tensors() const {
if (n_created != n_tensors) {
throw std::runtime_error(format("%s: wrong number of tensors; expected %d, got %d", __func__, n_tensors, n_created));
void llama_model_loader::done_getting_tensors(bool partial) const {
if (n_created > n_tensors) {
throw std::runtime_error(format("%s: too many tensors created; expected %d, got %d", __func__, n_tensors, n_created));
}
if (n_created < n_tensors) {
if (!partial) {
throw std::runtime_error(format("%s: wrong number of tensors; expected %d, got %d", __func__, n_tensors, n_created));
}
LLAMA_LOG_INFO("%s: partial load — used %d of %d tensors in the file (rest belong to a sibling model on the same .gguf)\n",
__func__, n_created, n_tensors);
}
if (n_tensors_moved > 0) {
LLAMA_LOG_DEBUG("%s: tensor '%s' (%s) (and %zu others) cannot be used with preferred buffer type %s, using %s instead\n",