Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-03 11:35:48 +02:00
Code Issues Packages Projects Releases Wiki Activity

sd: sync to master-431-23fce0b (#1893)

Browse Source 
* sd: sync to master-427-78e15bd

* add kl_optimal to the available schedulers list

* more robust workaround to avoid stb linkage issues

* sd: sync to master-431-23fce0b

* add TAEHV support and disable TAE if the model isn't found
This commit is contained in:
Wagner Bruna
2025-12-22 04:07:09 -03:00
committed by GitHub
parent 27c53099f4
commit 44ce1a80b3
11 changed files with 787 additions and 196 deletions
Download Patch File Download Diff File Expand all files Collapse all files
otherarch/sdcpp/model.cpp
+12
View File
@@ -1574,6 +1574,11 @@ bool ModelLoader::load_tensors(on_new_tensor_cb_t on_new_tensor_cb, int n_thread
i64_to_i32_vec((int64_t*)read_buf, (int32_t*)target_buf, tensor_storage.nelements());
}
if (tensor_storage.type != dst_tensor->type) {
if (convert_buf == nullptr) {
LOG_ERROR("read tensor data failed: too less memory for conversion");
failed = true;
return;
}
convert_tensor((void*)target_buf,
tensor_storage.type,
convert_buf,
@@ -1786,6 +1791,13 @@ bool ModelLoader::save_to_gguf_file(const std::string& file_path, ggml_type type
// tensor_storage.ne[0], tensor_storage.ne[1], tensor_storage.ne[2], tensor_storage.ne[3],
// tensor->n_dims, tensor->ne[0], tensor->ne[1], tensor->ne[2], tensor->ne[3]);
if (!tensor->data) {
GGML_ASSERT(ggml_nelements(tensor) == 0);
// avoid crashing the gguf writer by setting a dummy pointer for zero-sized tensors
LOG_DEBUG("setting dummy pointer for zero-sized tensor %s", name.c_str());
tensor->data = ggml_get_mem_buffer(ggml_ctx);
}
*dst_tensor = tensor;
gguf_add_tensor(gguf_ctx, tensor);