207 KB single binary. NPU 291 tok/s fused · GPU 307 tok/s ternary · GPU 383 tok/s 1-bit. 73+ models. NPU + GPU + CPU. Zero Python. MIT.
vulkan zig image-generation mit-license video-generation model-agnostic cplusplus-23 audio-generation local-llm open-source-ai stable-audio amd-strix-halo npu-inference one-binary-to-rule-them-all fused-engine xdna-2 zero-python zaya amd-native
-
Updated
Jul 12, 2026 - Zig