public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-21 18:19:35 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-08 14:36:36 +03:00
parent 4df9a57df2
commit 84bd03a438
151 changed files with 3439 additions and 871 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-adapter.cpp
+4 -4
View File
@@ -41,7 +41,7 @@ bool llama_adapter_cvec::init(const llama_model & model) {
auto it = ctx_map.find(buft);
if (it == ctx_map.end()) {
ggml_init_params params = {
/*.mem_size =*/ hparams.n_layer*ggml_tensor_overhead(),
/*.mem_size =*/ hparams.n_layer()*ggml_tensor_overhead(),
/*.mem_buffer =*/ NULL,
/*.no_alloc =*/ true,
};
@@ -61,9 +61,9 @@ bool llama_adapter_cvec::init(const llama_model & model) {
};
// make tensors
tensors.reserve(hparams.n_layer);
tensors.reserve(hparams.n_layer());
tensors.push_back(nullptr); // there's never a tensor for layer 0
for (size_t il = 1; il < hparams.n_layer; il++) {
for (size_t il = 1; il < hparams.n_layer(); il++) {
ggml_backend_buffer_type_t buft = model.select_buft(il);
ggml_context * ctx = ctx_for_buft(buft);
if (!ctx) {
@@ -121,7 +121,7 @@ bool llama_adapter_cvec::apply(
layer_start = il_start;
layer_end = il_end;
for (size_t il = 1; il < hparams.n_layer; il++) {
for (size_t il = 1; il < hparams.n_layer(); il++) {
assert(tensors[il] != nullptr);
const size_t off = n_embd * (il - 1); // buffer doesn't have data for layer 0, since it's never present