localai-org-maint-botandEttore Di Giacinto 5a24c8a2a2 fix(qwen-tts): restore CUDA 13 SDPA fallback (#12067) ...

The CUDA 13 profile resolves PyTorch 2.14. Its headers cannot build the
current FlashAttention source release under C++17, so the full backend
matrix cannot publish the image.

Leave FlashAttention optional on CUDA 13. The backend already retries
model loading with SDPA when FlashAttention is unavailable.

Assisted-by: Codex:gpt-5

Co-authored-by: Ettore Di Giacinto <mudler@localai.io>

2026-09-15 15:30:23 +02:00

..

backend.py

feat: materialize Hugging Face model artifacts (#10825)

2026-07-15 01:09:33 +02:00

install.sh

fix(qwen-tts): restore CUDA 13 SDPA fallback (#12067)

2026-09-15 15:30:23 +02:00

Makefile

feat(qwen-tts): add Qwen-tts backend (#8163)

2026-01-23 15:18:41 +01:00

requirements-cpu.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-cublas12-after.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-cublas12.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-cublas13.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-hipblas.txt

feat(rocm): bump to 7.x (#9323)

2026-04-12 08:51:30 +02:00

requirements-intel-after.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-intel.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-l4t12.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-l4t13.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

requirements-mps.txt

chore: update torch and torchaudio version specifications for qwen-tts in MPS

2026-02-04 16:55:42 +01:00

requirements.txt

fix(qwen-tts): ensure all requirements files end with newline (#8724)

2026-03-02 13:56:11 +01:00

run.sh

feat(qwen-tts): add Qwen-tts backend (#8163)

2026-01-23 15:18:41 +01:00

test.py

chore(ci): enlarge sleep startup time

2026-02-03 22:07:07 +01:00

test.sh

fix(qwen-tts): restore CUDA 13 SDPA fallback (#12067)

2026-09-15 15:30:23 +02:00