vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

wip cleanup before big merge

Browse source
This commit is contained in:
Concedo 2023-05-20 12:48:28 +08:00
parent 010b2753d9
commit 4e86a07e57
5 changed files with 2976 additions and 2989 deletions
Download patch file Download diff file Expand all files Collapse all files

2978
ggml.c
View file

File diff suppressed because it is too large Load diff

2984
ggml_v2.c
View file

File diff suppressed because it is too large Load diff

1
llama.cpp
View file

@ -1080,7 +1080,6 @@ static void llama_model_load_internal(
const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer)); const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
if(GetQuantsUnshuffled()) if(GetQuantsUnshuffled())
{ {
SetGPULayers(n_gpu);
fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu); fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);

1
otherarch/gpt2_v2.cpp
View file

@ -333,7 +333,6 @@ ModelLoadResult gpt2_model_load(const std::string & fname, gpt2_model & model, g
// const int n_gpu = std::min(gpulayers, int(hparams.n_layer)); // const int n_gpu = std::min(gpulayers, int(hparams.n_layer));
// if(GetQuantsUnshuffled()) // if(GetQuantsUnshuffled())
// { // {
// SetGPULayers(n_gpu);
// fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu); // fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);

1
otherarch/gptj_v2.cpp
View file

@ -336,7 +336,6 @@ ModelLoadResult gptj_model_load(const std::string & fname, gptj_model & model, g
// const int n_gpu = std::min(gpulayers, int(hparams.n_layer)); // const int n_gpu = std::min(gpulayers, int(hparams.n_layer));
// if(GetQuantsUnshuffled()) // if(GetQuantsUnshuffled())
// { // {
// SetGPULayers(n_gpu);
// fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu); // fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);