tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-13 20:07:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA GPU acceleration for LoRAs + f16 models (#1970)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-06-28 18:35:54 +02:00
committed by GitHub
parent cfa0750bc9
commit 7f9753fa12
4 changed files with 78 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/common.cpp
View File

@@ -416,13 +416,6 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
exit(1);
}
#ifdef GGML_USE_CUBLAS
if (!params.lora_adapter.empty() && params.n_gpu_layers > 0) {
fprintf(stderr, "%s: error: the simultaneous use of LoRAs and GPU acceleration is not supported", __func__);
exit(1);
}
#endif // GGML_USE_CUBLAS
if (escape_prompt) {
process_escapes(params.prompt);
}