From: Daniel Bevenius <redacted>
Date: Wed, 14 Jan 2026 09:31:49 +0000 (+0100)
Subject: CUDA : fix typo in clang pragma comment [no ci] (llama/18830)
X-Git-Tag: upstream/1.8.3+155~149
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=25aeb66a4a56bc20430e564d1c7815109a5cb801;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

CUDA : fix typo in clang pragma comment [no ci] (llama/18830)
---

diff --git a/ggml/src/ggml-cuda/fattn-vec.cuh b/ggml/src/ggml-cuda/fattn-vec.cuh
index 4d167b95..86f4dc0f 100644
--- a/ggml/src/ggml-cuda/fattn-vec.cuh
+++ b/ggml/src/ggml-cuda/fattn-vec.cuh
@@ -10,7 +10,7 @@ static constexpr __device__ int ggml_cuda_fattn_vec_get_nthreads_device() {
     return 128;
 }
 
-// Currenlty llvm with the amdgcn target dose not support unrolling loops
+// Currenlty llvm with the amdgcn target does not support unrolling loops
 // that contain a break that can not be resolved at compile time.
 #ifdef __clang__
 #pragma clang diagnostic push