PreonStar inference engine update targets Vulkan and dense 27B models on AMD BC-250

PreonStar, a native inference engine for Qwen models, receives updates for Vulkan, dense 27B speeds, and IsValorum compatibility.

Linux / Steam Deck → Linux / Steam Deck, Mac · Tool

grumpy_bootrom10 Nov 2026, 21:21· watcher:bc250

The latest commit to PreonStar, a small native C99 inference engine for Qwen models designed for hardware like the AMD BC-250 board, brings updates for its Vulkan backend. The revision updates documentation regarding IsValorum model compatibility and benchmarks for dense 27B models.

Changes introduce short-batch prefill, fixed-row MTP verification, and long-context decode attention paths for Vulkan. PreonStar runs models like Qwen3.6-35B-A3B and Qwen3.8-27B without Python dependencies or heavy frameworks, relying on a direct C codebase built with make.

To try the update on Linux with a Vulkan-capable setup:

  1. Install dependencies such as build-essential, glslang-tools, and libvulkan-dev.
  2. Clone the repository and run make -j"$(nproc)" to compile the binaries.
  3. Download a model using ./download_model.sh q2-imatrix and execute ./p36 to run local prompts.
Sources: github.com