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

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

backend-run-intel-env_test.sh

feat(sycl): make the intel llama.cpp backend self-contained on any host (#10991)

2026-07-31 23:39:53 +02:00

backend-signing_test.sh

fix(ci): remove unsupported cosign bundle flag (#11413)

2026-08-07 17:51:31 +02:00

bonsai-json-compat_test.sh

chore: ⬆️ Update ggml-org/llama.cpp to f280b26983ad0fdb705a0d9ebf0503e76f2899b0 (#11646)

2026-08-25 12:57:12 +02:00

ds4-darwin.sh

chore: ⬆️ Update antirez/ds4 to e34a8086693ba7ca5cfabd2b9028ee52f0bfac2e (#10350)

2026-06-16 09:59:50 +02:00

extract-vllm-metal-version_test.sh

fix(ci): unbreak the e2e build and the darwin vllm-metal pin (#11849)

2026-09-03 18:32:02 +02:00

fish-speech-ptxas_test.sh

fix(fish-speech): use CUDA toolkit ptxas

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

golang-darwin.sh

fix(backends): derive darwin RUN_BINARY from the exec line only (#10541)

2026-06-27 02:05:40 +02:00

healthcheck_test.sh

fix(worker): give the worker a real health endpoint and a mode-aware HEALTHCHECK (#10999)

2026-07-20 23:07:27 +02:00

healthcheck.sh

fix(worker): give the worker a real health endpoint and a mode-aware HEALTHCHECK (#10999)

2026-07-20 23:07:27 +02:00

llama-cpp-build-target_test.sh

fix(rocm): stop building the ggml CPU variant matrix for hipblas llama.cpp (#11346)

2026-08-04 15:55:58 +02:00

llama-cpp-darwin.sh

feat: single-build ggml CPU_ALL_VARIANTS for llama-cpp + turboquant (x86/arm64/apple) (#10497)

2026-06-25 15:47:03 +02:00

package-gpu-libs_test.sh

fix(gpu-libs): bundle transitive deps of GPU runtime libs (#10537) (#10539)

2026-06-27 01:36:33 +02:00

package-gpu-libs-cudnn_test.sh

fix(gpu-libs): bundle cuDNN only where it is used, and complete it when it is (#10946)

2026-07-19 07:48:51 +00:00

package-gpu-libs-intel_test.sh

feat(sycl): make the intel llama.cpp backend self-contained on any host (#10991)

2026-07-31 23:39:53 +02:00

package-gpu-libs-rocm-data_test.sh

fix(gpu-libs): bundle hipBLASLt TensileLibrary data so ROCm backends stop falling back (#10660) (#10672) the

2026-07-04 08:14:12 +02:00

package-gpu-libs.sh

feat(sycl): make the intel llama.cpp backend self-contained on any host (#10991)

2026-07-31 23:39:53 +02:00

package-system-libs.sh

refactor(backends): extract package-system-libs.sh from 31 package.sh (#11095)

2026-07-30 16:30:49 +02:00

privacy-filter-darwin.sh

feat(backends): darwin/Metal build for the privacy-filter backend (#10513)

2026-06-26 01:18:41 +02:00

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

Add mlx-vlm (#6119)

2025-08-23 23:05:30 +02:00

stablediffusion-metal-build_test.sh

fix(stablediffusion): embed Metal library (#11531)

2026-08-15 13:15:55 +02:00

turboquant-build-target_test.sh

fix(sycl): stop building the ggml CPU variant matrix with icpx (#11321)

2026-08-03 19:00:00 +02:00