From: Akarshan Biswas <redacted>
Date: Tue, 26 Aug 2025 18:57:49 +0000 (+0530)
Subject: SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (#15592)
X-Git-Tag: upstream/0.0.6527~234
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=8b696861364360770e9f61a3422d32941a477824;p=pkg%2Fggml%2Fsources%2Fllama.cpp

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.
---

diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp
index 12dd5dd2..18ff4e0b 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: