From 3d7ebf63123b8652fb7bbecef7ba731202309901 Mon Sep 17 00:00:00 2001 From: 0cc4m Date: Mon, 3 Jun 2024 10:59:14 +0200 Subject: Vulkan Mixture of Experts (MoE) support (#7628) * Finish Vulkan mul_mat_id implementation * Add Vulkan sum_rows and div ops * Fix MUL_MAT_ID matrix matrix shader * Fix MUL_MAT_ID matrix vector shader dispatch size * Fix MUL_MAT_ID matrix vector shader and dispatch code * Update Vulkan CPU offload for MUL_MAT_ID * Fix crash when using split mode none and setting a main GPU --- common/common.cpp | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'common/common.cpp') diff --git a/common/common.cpp b/common/common.cpp index 65103c3c..022bfe28 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1002,9 +1002,9 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa return true; } params.main_gpu = std::stoi(argv[i]); -#ifndef GGML_USE_CUDA_SYCL - fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL. Setting the main GPU has no effect.\n"); -#endif // GGML_USE_CUDA_SYCL +#ifndef GGML_USE_CUDA_SYCL_VULKAN + fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL/Vulkan. Setting the main GPU has no effect.\n"); +#endif // GGML_USE_CUDA_SYCL_VULKAN return true; } if (arg == "--split-mode" || arg == "-sm") { @@ -1030,9 +1030,9 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa invalid_param = true; return true; } -#ifndef GGML_USE_CUDA_SYCL - fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL. Setting the split mode has no effect.\n"); -#endif // GGML_USE_CUDA_SYCL +#ifndef GGML_USE_CUDA_SYCL_VULKAN + fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL/Vulkan. Setting the split mode has no effect.\n"); +#endif // GGML_USE_CUDA_SYCL_VULKAN return true; } if (arg == "--tensor-split" || arg == "-ts") { -- cgit v1.2.3