From 46c693dcb9c358f9ad6054967e626a3acd658807 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 10 Mar 2026 12:28:59 +0200 Subject: [PATCH] cont : fix the fix Co-authored-by: Aman Gupta --- ggml/src/ggml-cuda/ggml-cuda.cu | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu index c35b37fd61..676fa7929f 100644 --- a/ggml/src/ggml-cuda/ggml-cuda.cu +++ b/ggml/src/ggml-cuda/ggml-cuda.cu @@ -4999,7 +4999,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g #ifdef GGML_USE_MUSA return false; #else - KDA is faster using the AR kernel even when n_tokens >= 512. + // KDA is faster using the AR kernel even when n_tokens >= 512. //TODO: Add chunked kernel return op->src[0]->ne[2] == 1 || op->src[3]->ne[0] == op->src[2]->ne[0]; #endif // GGML_USE_MUSA