CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

kompute : fix fallback to CPU (#5201)

Browse Source
This commit is contained in:
Jared Van Bortel
2024-01-29 17:11:27 -05:00
committed by GitHub
parent fbf1ddec69
commit 6daa69ee81
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@@ -4136,7 +4136,7 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam
} }
#ifdef GGML_USE_KOMPUTE #ifdef GGML_USE_KOMPUTE
if (ggml_vk_has_device() && params.n_gpu_layers > 0 && ( if (params.n_gpu_layers > 0 && (
!(model.arch == LLM_ARCH_LLAMA || model.arch == LLM_ARCH_FALCON) !(model.arch == LLM_ARCH_LLAMA || model.arch == LLM_ARCH_FALCON)
|| !( || !(
model.ftype == LLAMA_FTYPE_ALL_F32 || model.ftype == LLAMA_FTYPE_ALL_F32 ||
@@ -4145,8 +4145,8 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam
model.ftype == LLAMA_FTYPE_MOSTLY_Q4_1 model.ftype == LLAMA_FTYPE_MOSTLY_Q4_1
) )
)) { )) {
// disable Vulkan due to unsupported model architecture or quantization type
// TODO(cebtenzzre): propagate this error outside of llama_load_model_from_file // TODO(cebtenzzre): propagate this error outside of llama_load_model_from_file
LLAMA_LOG_WARN("%s: disabling Kompute due to unsupported model arch or quantization\n", __func__);
params.n_gpu_layers = 0; params.n_gpu_layers = 0;
} }
#endif #endif