diff --git a/llama.cpp b/llama.cpp
index 858494244..f5e0eac81 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -6510,7 +6510,6 @@ struct llama_context * llama_new_context_with_model(
 #undef LLAMA_METAL_CHECK_BUF
         }
 #elif defined(GGML_USE_KOMPUTE)
-    // TODO(cebtenzzre): we need to check the type of each tensor because Q8_0 is not currently supported
     if (ggml_vk_has_device() && params.n_gpu_layers > 0
         && (model->arch == LLM_ARCH_LLAMA || model->arch == LLM_ARCH_FALCON)
         && (model->ftype == LLAMA_FTYPE_ALL_F32