vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-06 12:29:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix error in llama_context_n_gpu_layers

Browse source
This commit is contained in:
Lizonghang 2025-01-15 10:08:41 +04:00
parent 5d9aadf3d5
commit 9279a2e3ff
3 changed files with 0 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
common/common.cpp
View file

@ -1440,7 +1440,6 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
params.n_gpu_layers = n_gpu_layers[my_rank];
cparams.n_gpu_layers = n_gpu_layers[my_rank];
mparams.n_gpu_layers = n_gpu_layers[my_rank];
llama_context_n_gpu_layers(lctx)[my_rank] = n_gpu_layers[my_rank];
#ifdef LLAMA_DEBUG
device_print_props(dev_info_set, n_world, model, cparams);

2
include/llama.h
View file

@ -465,8 +465,6 @@ extern "C" {
LLAMA_API uint32_t * llama_context_n_layer_window(struct llama_context * ctx);
LLAMA_API uint32_t * llama_context_n_gpu_layers(struct llama_context * ctx);
// Frees all allocated memory
LLAMA_API void llama_free(struct llama_context * ctx);

4
src/llama.cpp
View file

@ -20519,10 +20519,6 @@ uint32_t * llama_context_n_layer_window(struct llama_context * ctx) {
return ctx->cparams.n_layer_window;
}
uint32_t * llama_context_n_gpu_layers(struct llama_context * ctx) {
return ctx->cparams.n_gpu_layers;
}
void llama_free(struct llama_context * ctx) {
delete ctx;
}