CUDA backend confirmed broken for fish-speech ops on s2.cpp v0.x — alpha,
incomplete op coverage, GPU stays at 0% during generation despite
ggml_cuda_init succeeding. Vulkan was the original README example
(`-v 0`), so likely the more battle-tested path.
Build the image with BOTH backends so we can flip via env without
rebuilding:
* libvulkan-dev + glslc in the build stage (GGML's Vulkan backend
compiles its shaders with glslc at build time; without it the
cmake configure silently disables Vulkan).
* libvulkan1 + the libggml-vulkan.so copy in the runtime stage.
* compose env NVIDIA_DRIVER_CAPABILITIES=compute,utility,graphics —
default nvidia-container-toolkit only mounts compute libs; Vulkan
needs the graphics ICD (libGLX_nvidia + nvidia_icd.json) too.
* entrypoint reads FISH_CPP_BACKEND (cuda/vulkan/cpu) and selects
the appropriate -c/-v/no-flag invocation.
* Default backend = vulkan.
vh
67813bbef4