From 21999481eaee2318a07b34c3d2d61aad1325c1c4 Mon Sep 17 00:00:00 2001 From: Jon Haus Date: Sun, 12 Jan 2025 17:42:24 -0500 Subject: [PATCH] cuda: Use common gfx8 value for GCN4 rocm_agent_enumerator returns the two values 800 and 803 with the former being used by this API --- ggml/src/ggml-cuda/common.cuh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ggml/src/ggml-cuda/common.cuh b/ggml/src/ggml-cuda/common.cuh index 2c0a56226..1bda18a2d 100644 --- a/ggml/src/ggml-cuda/common.cuh +++ b/ggml/src/ggml-cuda/common.cuh @@ -49,7 +49,7 @@ #define GGML_CUDA_CC_OFFSET_AMD 1000000 // GCN/CNDA, wave size is 64 -#define GGML_CUDA_CC_GCN4 (GGML_CUDA_CC_OFFSET_AMD + 803) // Tonga, Fiji, Polaris, minimum for fast fp16 +#define GGML_CUDA_CC_GCN4 (GGML_CUDA_CC_OFFSET_AMD + 800) // Tonga, Fiji, Polaris, minimum for fast fp16 #define GGML_CUDA_CC_VEGA (GGML_CUDA_CC_OFFSET_AMD + 900) // Vega56/64, minimum for fp16 dual issue #define GGML_CUDA_CC_VEGA20 (GGML_CUDA_CC_OFFSET_AMD + 906) // MI50/Radeon VII, minimum for dp4a #define GGML_CUDA_CC_CDNA (GGML_CUDA_CC_OFFSET_AMD + 908) // MI100, minimum for MFMA, acc registers