From 5cb04dbc16d1da38c8fdcc0111b40e67d00dd1c3 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Wed, 31 Jan 2024 17:30:17 +0200 Subject: llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240) * llama : remove LLAMA_MAX_DEVICES from llama.h ggml-ci * Update llama.cpp Co-authored-by: slaren * server : remove LLAMA_MAX_DEVICES ggml-ci * llama : remove LLAMA_SUPPORTS_GPU_OFFLOAD ggml-ci * train : remove LLAMA_SUPPORTS_GPU_OFFLOAD * readme : add deprecation notice * readme : change deprecation notice to "remove" and fix url * llama : remove gpu includes from llama.h ggml-ci --------- Co-authored-by: slaren --- examples/batched-bench/batched-bench.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/batched-bench') diff --git a/examples/batched-bench/batched-bench.cpp b/examples/batched-bench/batched-bench.cpp index 7924db26..b52d6845 100644 --- a/examples/batched-bench/batched-bench.cpp +++ b/examples/batched-bench/batched-bench.cpp @@ -88,7 +88,7 @@ int main(int argc, char ** argv) { llama_model_params model_params = llama_model_default_params(); - const std::vector t_split (LLAMA_MAX_DEVICES, 0.0f); + const std::vector t_split(llama_max_devices(), 0.0f); model_params.n_gpu_layers = n_gpu_layers; model_params.tensor_split = t_split.data(); -- cgit v1.2.3