From 7959e937a10bb935d5682701ae01e5a51c3157e3 Mon Sep 17 00:00:00 2001 From: Concedo <39025047+LostRuins@users.noreply.github.com> Date: Wed, 26 Jun 2024 14:32:58 +0800 Subject: [PATCH] Revert "set flags to optimize for mmq" This reverts commit 8ad0d29ef8d4c4ae6408a612535ae8828fc512c2. --- ggml-cuda/mmq.cuh | 1 - 1 file changed, 1 deletion(-) diff --git a/ggml-cuda/mmq.cuh b/ggml-cuda/mmq.cuh index f97bbd6e7..d59c0532f 100644 --- a/ggml-cuda/mmq.cuh +++ b/ggml-cuda/mmq.cuh @@ -8,7 +8,6 @@ #include #define MMQ_DP4A_MAX_BATCH_SIZE 64 // Max. batch size to use for dp4a MMQ kernels when FP16 tensor cores are available. -#define GGML_CUDA_FORCE_MMQ typedef void (*load_tiles_mmq_t)(const char * __restrict__ x, int * x_tile, const int & kbx0, const int & i_max, const int & stride); typedef void (*vec_dot_mmq_t)(const int * __restrict__ x, const int * __restrict__ y, float * __restrict__ sum, const int & k0);