Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix talk-llama build after ggml sync (commit 5feb0dffbae5). #1049

Merged
merged 1 commit into from
Jun 25, 2023
Merged

Fix talk-llama build after ggml sync (commit 5feb0dffbae5). #1049

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions examples/talk-llama/llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1002,7 +1002,7 @@ static void llama_model_load_internal(
}

#ifdef GGML_USE_CUBLAS
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CUDA
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_GPU
#else
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CPU
#endif
Expand Down Expand Up @@ -1054,7 +1054,7 @@ static void llama_model_load_internal(
layer.w2 = ml->get_tensor(layers_i + ".feed_forward.w2.weight", { n_ff, n_embd}, backend);
layer.w3 = ml->get_tensor(layers_i + ".feed_forward.w3.weight", {n_embd, n_ff}, backend);

if (backend == GGML_BACKEND_CUDA) {
if (backend == GGML_BACKEND_GPU) {
vram_total +=
ggml_nbytes(layer.attention_norm) + ggml_nbytes(layer.wq) + ggml_nbytes(layer.wk) +
ggml_nbytes(layer.wv) + ggml_nbytes(layer.wo) + ggml_nbytes(layer.attention_norm) +
Expand Down Expand Up @@ -1115,7 +1115,7 @@ static void llama_model_load_internal(
}
}
for (llama_load_tensor & lt : ml->tensors_map.tensors) {
if (lt.ggml_tensor->backend != GGML_BACKEND_CUDA) {
if (lt.ggml_tensor->backend != GGML_BACKEND_GPU) {
continue;
}
if (progress_callback) {
Expand Down