3 Commits

Include renames

Author	SHA1	Message	Date
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
Ettore Di Giacinto	1dfa25e681	fix(qwen-tts): limit CUDA compiler threads ... The CUDA 13 FlashAttention build still exhausts hosted-runner memory with a single ninja worker because nvcc can compile multiple threads internally. Limit nvcc to one thread for that profile and guard the setting in the backend test script. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-11 23:19:28 +00:00
Ettore Di Giacinto	923ebbb344	feat(qwen-tts): add Qwen-tts backend (#8163) ... * feat(qwen-tts): add Qwen-tts backend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Update intel deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop flash-attn for cuda13 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-01-23 15:18:41 +01:00