From bcac6c42eaf9e004716d72960bddefb1db68a93c Mon Sep 17 00:00:00 2001 From: historia Date: Tue, 25 Aug 2026 17:41:58 -0400 Subject: fix: build audio.cpp with --deployment-build --- app/docs/backend-audiocpp.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'app/docs/backend-audiocpp.md') diff --git a/app/docs/backend-audiocpp.md b/app/docs/backend-audiocpp.md index 926dc6a..318e629 100644 --- a/app/docs/backend-audiocpp.md +++ b/app/docs/backend-audiocpp.md @@ -15,9 +15,11 @@ Download and build `audiocpp_server` for your platform and backend `(cuda, vulka ```bash git clone https://github.com/0xShug0/audio.cpp cd audio.cpp -scripts/build_linux.sh --backend cuda --target audiocpp_server +scripts/build_linux.sh --backend cuda --target audiocpp_server --deployment-build ``` +`--deployment-build` compiles the `model_specs/` catalog into the binary so every family resolves its model contract even when the server is started outside the checkout (GGUF packages whose embedded spec is legacy, such as today's Qwen3-TTS ones, otherwise need `model_specs/.json` found relative to the working directory). The macOS script takes the same flag; the Windows PowerShell scripts take `-DeploymentBuild`. + ### Install models Download model packages with the python model manager script from the audio.cpp checkout. Each installs to `./models`. Here are two examples, Higgs Audio and Qwen3-TTS: -- cgit v1.2.3