From 6bbc598a632560cb45dd2c51ad403bda8723b629 Mon Sep 17 00:00:00 2001 From: Henri Vasserman Date: Fri, 25 Aug 2023 12:09:42 +0300 Subject: ROCm Port (#1087) * use hipblas based on cublas * Update Makefile for the Cuda kernels * Expand arch list and make it overrideable * Fix multi GPU on multiple amd architectures with rocblas_initialize() (#5) * add hipBLAS to README * new build arg LLAMA_CUDA_MMQ_Y * fix half2 decomposition * Add intrinsics polyfills for AMD * AMD assembly optimized __dp4a * Allow overriding CC_TURING * use "ROCm" instead of "CUDA" * ignore all build dirs * Add Dockerfiles * fix llama-bench * fix -nommq help for non CUDA/HIP --------- Co-authored-by: YellowRoseCx <80486540+YellowRoseCx@users.noreply.github.com> Co-authored-by: ardfork <134447697+ardfork@users.noreply.github.com> Co-authored-by: funnbot <22226942+funnbot@users.noreply.github.com> Co-authored-by: Engininja2 <139037756+Engininja2@users.noreply.github.com> Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com> Co-authored-by: jammm <2500920+jammm@users.noreply.github.com> Co-authored-by: jdecourval <7315817+jdecourval@users.noreply.github.com> --- examples/llama-bench/llama-bench.cpp | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'examples/llama-bench/llama-bench.cpp') diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index 36057bfc..7a281158 100755 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -18,9 +18,7 @@ #include "llama.h" #include "common.h" #include "build-info.h" -#ifdef GGML_USE_CUBLAS #include "ggml-cuda.h" -#endif // utils static uint64_t get_time_ns() { @@ -504,7 +502,7 @@ struct test { static std::string get_backend() { if (cuda) { - return "CUDA"; + return GGML_CUDA_NAME; } if (opencl) { return "OpenCL"; -- cgit v1.2.3