Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model : allow reshape of tensors during load (#26531)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-08-04 09:06:44 +03:00
committed by GitHub
parent 935cad6497
commit 1269cb1ff1
5 changed files with 60 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.h
+6 -3
View File
@@ -67,6 +67,7 @@ struct llama_model_loader {
static const int TENSOR_DUPLICATED = 1 << 1;
static const int TENSOR_SKIP = 1 << 2;
static const int TENSOR_SKIP_IF_VIRTUAL = 1 << 3;
static const int TENSOR_ALLOW_RESHAPE = 1 << 4;
int n_kv = 0;
int n_tensors = 0;
@@ -177,14 +178,16 @@ struct llama_model_loader {
struct ggml_tensor * require_tensor_meta(const std::string & name) const;
const struct ggml_tensor * check_tensor_dims(const std::string & name, const std::vector<int64_t> & ne, bool required) const;
const struct ggml_tensor * check_tensor_dims(
const std::string & name,
const std::vector<int64_t> & ne,
bool required,
bool allow_reshape) const;
struct ggml_tensor * create_tensor(
const llama_hparams & hparams, const buft_list_t * buft_list_cpu, const buft_list_t * buft_list_input, const buft_list_t * buft_list_output,
const buft_list_t * buft_list_layer, const LLM_TN_IMPL & tn, const std::initializer_list<int64_t> & ne, int flags);
struct ggml_tensor * create_tensor_as_view(struct ggml_context * ctx, struct ggml_tensor * base, const std::string & name, const std::initializer_list<int64_t> & ne, size_t offset, bool required = true);
void done_getting_tensors(bool partial = false) const;
void init_mappings(bool prefetch = true, llama_mlocks * mlock_mmaps = nullptr);