Update blog

Author: cmdr2

content/blog/2025-10-10-1760088945.md

@@ -12,9 +12,7 @@ Some notes on machine-learning compilers, gathered while researching tech for Ea
 
 ## tl;dr summary
 
-// This analysis could change in the future!
-
-The current state is:
+The current state is (could change in the future!):
 1. Vendor-specific compilers are the only performant options on consumer GPUs. For e.g. [TensorRT-RTX](https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/index.html) for NVIDIA, [MiGraphX](https://rocm.docs.amd.com/projects/AMDMIGraphX/en/latest/) for AMD, [OpenVINO](https://github.com/openvinotoolkit/openvino) for Intel.
 2. Cross-vendor compilers are just not performant enough for Stable Diffusion-class workloads on consumer GPUs. For e.g. like [TVM](https://tvm.apache.org/), [IREE](https://iree.dev/), [XLA](https://openxla.org/xla).