diff options
| -rw-r--r-- | llama.cpp | 11 |
1 files changed, 6 insertions, 5 deletions
@@ -5164,11 +5164,12 @@ static int llama_decode_internal( // If all tensors can be run on the GPU then using more than 1 thread is detrimental. const bool full_offload_supported = - model.arch == LLM_ARCH_LLAMA || - model.arch == LLM_ARCH_BAICHUAN || - model.arch == LLM_ARCH_FALCON || - model.arch == LLM_ARCH_REFACT || - model.arch == LLM_ARCH_MPT; + model.arch == LLM_ARCH_LLAMA || + model.arch == LLM_ARCH_BAICHUAN || + model.arch == LLM_ARCH_FALCON || + model.arch == LLM_ARCH_REFACT || + model.arch == LLM_ARCH_MPT || + model.arch == LLM_ARCH_STARCODER; const bool fully_offloaded = model.n_gpu_layers >= (int) hparams.n_layer + 3; if (ggml_cpu_has_cublas() && full_offload_supported && fully_offloaded) { |