Ettore Di Giacinto f5ea6e4eab fix(fish-speech): use CUDA toolkit ptxas ...

Prefer an explicitly configured Triton assembler, otherwise use the executable ptxas from CUDA_HOME so torch.compile can target GPU architectures newer than Triton bundled tooling.

Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-09-11 21:48:54 +00:00

..

audio-cpp-darwin.sh

…

backend-run-intel-env_test.sh

…

backend-signing_test.sh

…

bonsai-json-compat_test.sh

…

ds4-darwin.sh

…

extract-vllm-metal-version_test.sh

…

fish-speech-ptxas_test.sh

fix(fish-speech): use CUDA toolkit ptxas

2026-09-11 21:48:54 +00:00

golang-darwin.sh

…

healthcheck_test.sh

…

healthcheck.sh

…

llama-cpp-build-target_test.sh

…

llama-cpp-darwin.sh

…

package-gpu-libs_test.sh

…

package-gpu-libs-cudnn_test.sh

…

package-gpu-libs-intel_test.sh

…

package-gpu-libs-rocm-data_test.sh

…

package-gpu-libs.sh

…

package-system-libs.sh

…

privacy-filter-darwin.sh

…

python-backend-intel-runtime_test.sh

fix: prefer the Intel diffusers venv SYCL runtime at startup (#11971)

2026-09-11 12:13:03 +02:00

python-darwin.sh

…

stablediffusion-metal-build_test.sh

…

turboquant-build-target_test.sh

…