From 8b696861364360770e9f61a3422d32941a477824 Mon Sep 17 00:00:00 2001 From: Akarshan Biswas Date: Wed, 27 Aug 2025 00:27:49 +0530 Subject: [PATCH] SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (#15592) The original implementation unconditionally returned true for this operation, leading to a failure when the tensor's first dimension (ne[0]) was not a multiple of WARP_SIZE. This caused an GGML_ASSERT(ncols % WARP_SIZE == 0) failure in ggml-sycl/norm.cpp. This change updates the ggml_backend_sycl_device_supports_op check to correctly return true for GGML_OP_RMS_NORM only when the first dimension of the tensor is a multiple of WARP_SIZE, ensuring the operation can be performed without error. --- ggml/src/ggml-sycl/ggml-sycl.cpp | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp index 12dd5dd2e6..18ff4e0b0c 100644 --- a/ggml/src/ggml-sycl/ggml-sycl.cpp +++ b/ggml/src/ggml-sycl/ggml-sycl.cpp @@ -4364,11 +4364,12 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g return (op->type == GGML_TYPE_F32 && op->src[0]->type == GGML_TYPE_F32) && (op->type == op->src[0]->type); #endif case GGML_OP_NORM: - case GGML_OP_RMS_NORM: return true; case GGML_OP_L2_NORM: case GGML_OP_GROUP_NORM: return ggml_is_contiguous(op->src[0]); + case GGML_OP_RMS_NORM: + return ((op->src[0]->ne[0] % WARP_SIZE) == 0); case GGML_OP_SCALE: return true; case GGML_OP_CONT: