Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-11 04:56:56 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into qwen4exp/qwen3.8-flash-next

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-27 15:19:24 +02:00
parent 41b4b7073c fac889fb38
commit 539c35e940
84 changed files with 2321 additions and 1613 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+3 -1
View File
@@ -2681,6 +2681,7 @@ llama_model_params llama_model_default_params() {
/*.n_gpu_layers =*/ -1,
/*.split_mode =*/ LLAMA_SPLIT_MODE_LAYER,
/*.load_mode =*/ LLAMA_LOAD_MODE_AUTO,
/*.tensor_read_lazy =*/ LLAMA_TENSOR_READ_LAZY_AUTO,
/*.main_gpu =*/ 0,
/*.tensor_split =*/ nullptr,
/*.progress_callback =*/ nullptr,
@@ -3118,7 +3119,8 @@ llama_model_base::llama_model_base(const struct llama_model_params & params) : l
TENSOR_NOT_REQUIRED (llama_model_loader::TENSOR_NOT_REQUIRED),
TENSOR_SKIP (llama_model_loader::TENSOR_SKIP),
TENSOR_SKIP_IF_VIRTUAL(llama_model_loader::TENSOR_SKIP_IF_VIRTUAL),
TENSOR_ALLOW_RESHAPE (llama_model_loader::TENSOR_ALLOW_RESHAPE) {}
TENSOR_ALLOW_RESHAPE (llama_model_loader::TENSOR_ALLOW_RESHAPE),
TENSOR_READ_LAZY (llama_model_loader::TENSOR_READ_LAZY) {}
ggml_tensor * llama_model_base::create_tensor(const LLM_TN_IMPL & tn, const std::initializer_list<int64_t> & ne, int flags) {
GGML_ASSERT(ml != nullptr);