tzhouam 617c6ca55f feat: enhance model loading with prefetching and retry logic ...

- Introduced `from_pretrained_with_prefetch` to handle racy cache scenarios by re-prefetching and retrying on failures.
- Updated various model pipelines to utilize the new prefetching mechanism, ensuring robust loading of model components.
- Prefetch logic added to multiple models, including HunyuanVideo, LongCatImage, and QwenImage, to mitigate issues with incomplete cache states.

2026-06-02 09:01:47 +00:00

..

__init__.py

feat: add LTX-2.3 video generation model support (#2893)

2026-04-23 16:51:51 +08:00

ltx2_transformer.py

[Blackwell] Add CUDNN_ATTN and FLASHINFER_ATTN backends for diffusion (auto-route) (#3079)

2026-05-28 11:09:25 +08:00

pipeline_ltx2_3_image2video.py

feat: add LTX-2.3 video generation model support (#2893)

2026-04-23 16:51:51 +08:00

pipeline_ltx2_3.py

feat: enhance model loading with prefetching and retry logic

2026-06-02 09:01:47 +00:00

pipeline_ltx2_image2video.py

[CI][Bugfix] Fix LTX audio-video warmup output typing (#3964)

2026-05-29 07:46:02 +00:00

pipeline_ltx2_latent_upsample.py

[Model] Add two stages inference for model LTX-2 distilled. (#2260)

2026-04-03 23:17:49 +08:00

pipeline_ltx2.py

feat: enhance model loading with prefetching and retry logic

2026-06-02 09:01:47 +00:00