Tae: fix race condition causing inconsistent value for `decoder_only` #28

Job	Run time
ubuntu-latest-cmake	1m 59s
windows-latest-cmake (noavx, -DGGML_NATIVE=OFF -DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF -DSD...	1m 41s
macOS-latest-cmake	2m 9s
windows-latest-cmake (avx2, -DGGML_NATIVE=OFF -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON)	2m 21s
windows-latest-cmake (avx, -DGGML_NATIVE=OFF -DGGML_AVX=ON -DGGML_AVX2=OFF -DSD_BUILD_SHARED_LIBS...	1m 40s
windows-latest-cmake (avx512, -DGGML_NATIVE=OFF -DGGML_AVX512=ON -DGGML_AVX=ON -DGGML_AVX2=ON -DS...	1m 46s
windows-latest-cmake (cuda12, -DSD_CUDA=ON -DSD_BUILD_SHARED_LIBS=ON -DCMAKE_CUDA_ARCHITECTURES=9...	41m 22s
windows-latest-cmake (vulkan, -DSD_VULKAN=ON -DSD_BUILD_SHARED_LIBS=ON)	3m 17s
release	45s
	57m 0s

Provide feedback